Paper Digest: Recent Papers on Generative Adversarial Network
Paper Digest Team extracted all recent Generative Adversarial Network (GAN) related papers on our radar, and generated highlight sentences for them. The results are then sorted by relevance & date. In addition to this ‘static’ page, we also provide a real-time version of this article, which has more coverage and is updated in real time to include the most recent updates on this topic.
Based in New York, Paper Digest is dedicated to helping people generate contents & reason over unstructured data. Different from black-box approaches, we build deep models on semantics, which allows results to be produced with explainations. Such models power this website, and are behind our services including “search engine”, “summarization”, “question answering”, and “literature review”.
If you do not want to miss interesting academic papers, you are welcome to sign up our free daily paper digest service to get updates on new papers published in your area every day. You are also welcome to follow us on Twitter and Linkedin to get updated with new conference digests.
Paper Digest Team
New York City, New York, 10017
team@paperdigest.org
TABLE 1: Paper Digest: Recent Papers on Generative Adversarial Network
| Paper | Author(s) | Source | Date | |
|---|---|---|---|---|
| 1 | Denoising Diffusion Probabilistic Models for Probabilistic Energy Forecasting Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a recent promising deep learning generative approach: denoising diffusion probabilistic models. |
Esteban Hernandez; Jonathan Dumas; | arxiv-cs.LG | 2022-12-06 |
| 2 | Bayesian Learning with Information Gain Provably Bounds Risk for A Robust Adversarial Defense Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a new algorithm to learn a deep neural network model robust against adversarial attacks. |
Bao Gia Doan; Ehsan Abbasnejad; Javen Qinfeng Shi; Damith C. Ranasinghe; | arxiv-cs.LG | 2022-12-04 |
| 3 | Bitcoin Security-Latency Under Network Delay Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We improve security-latency bounds of Nakamoto consensus by analyzing the race between adversarial and honest chains in three different phases: pre-mining, confirmation and post-confirmation. |
Mustafa Doger; Sennur Ulukus; | arxiv-cs.CR | 2022-12-02 |
| 4 | GrannGAN: Graph Annotation Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The model we propose tackles the problem of generating the data features constrained by the specific graph structure of each data point by splitting the task into two phases. |
Yoann Boget; Magda Gregorova; Alexandros Kalousis; | arxiv-cs.LG | 2022-12-01 |
| 5 | AL-iGAN: An Active Learning Framework for Tunnel Geological Reconstruction Based on TBM Operational Data Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an active learning framework, called AL-iGAN, for tunnel geological reconstruction based on TBM operational data. |
Hao Wang; Lixue Liu; Xueguan Song; Chao Zhang; Dacheng Tao; | arxiv-cs.LG | 2022-12-01 |
| 6 | Adaptive Adversarial Training Method for Improving Multi-scale GAN Based on Generalization Bound Theory Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we pioneered the introduction of PAC-Bayes generalized bound theory into the training analysis of specific models under different adversarial training methods, which can obtain a non-vacuous upper bound on the generalization error for the specified multi-scale GAN structure. |
Jing Tang; Bo Tao; Zeyu Gong; Zhouping Yin; | arxiv-cs.CV | 2022-11-30 |
| 7 | Generative Adversarial Learning of Sinkhorn Algorithm Initializations Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We train a neural network to compute initializations for the algorithm, which significantly outperform standard initializations. |
Jonathan Geuter; Vaios Laschos; | arxiv-cs.LG | 2022-11-30 |
| 8 | VIDM: Video Implicit Diffusion Models Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a video generation method based on diffusion models, where the effects of motion are modeled in an implicit condition manner, i.e. one can sample plausible video motions according to the latent feature of frames. |
Kangfu Mei; Vishal M. Patel; | arxiv-cs.CV | 2022-11-30 |
| 9 | Efficient Adversarial Input Generation Via Neural Net Patching Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work presents a novel technique to patch neural networks and an innovative approach of using it to produce perturbations of inputs which are adversarial for the original net. |
Tooba Khan; Kumar Madhukar; Subodh Vishnu Sharma; | arxiv-cs.LG | 2022-11-30 |
| 10 | Three-stage Binarization of Color Document Images Based on Discrete Wavelet Transform and Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a three-stage method is proposed for image enhancement and binarization of degraded color document images by using discrete wavelet transform (DWT) and generative adversarial network (GAN). |
Yu-Shian Lin; Rui-Yang Ju; Chih-Chia Chen; Ting-Yu Lin; Jen-Shiun Chiang; | arxiv-cs.CV | 2022-11-29 |
| 11 | Balanced Semi-Supervised Generative Adversarial Network for Damage Assessment from Low-Data Imbalanced-Class Regime Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce one variant of the Generative Adversarial Network (GAN), named the balanced semi-supervised GAN (BSS-GAN). |
Yuqing Gao; Pengyuan Zhai; Khalid M. Mosalam; | arxiv-cs.LG | 2022-11-29 |
| 12 | Conditional Progressive Generative Adversarial Network for Satellite Image Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we formulate the image generation task as completion of an image where one out of three corners is missing. |
Renato Cardoso; Sofia Vallecorsa; Edoardo Nemni; | arxiv-cs.CV | 2022-11-28 |
| 13 | 3inGAN: Learning A 3D Generative Model from Images of A Self-similar Scene Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce 3inGAN, an unconditional 3D generative model trained from 2D images of a single self-similar 3D scene. |
Animesh Karnewar; Oliver Wang; Tobias Ritschel; Niloy Mitra; | arxiv-cs.CV | 2022-11-27 |
| 14 | Imperceptible Adversarial Attack Via Invertible Neural Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a novel Adversarial Attack via Invertible Neural Networks (AdvINN) method to produce robust and imperceptible adversarial examples. |
ZIHAN CHEN et. al. | arxiv-cs.CV | 2022-11-27 |
| 15 | Adversarial Rademacher Complexity of Deep Neural Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, such variants of Rademacher complexity are not guaranteed to be bounds for meaningful robust generalization gaps (RGG). In this paper, we provide a solution to this unsolved problem. |
Jiancong Xiao; Yanbo Fan; Ruoyu Sun; Zhi-Quan Luo; | arxiv-cs.LG | 2022-11-27 |
| 16 | Game Theoretic Mixed Experts for Combinational Adversarial Machine Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: A natural question arises: how can one best leverage a combination of adversarial defenses to thwart such attacks? In this paper, we provide a game-theoretic framework for ensemble adversarial attacks and defenses which answers this question. |
Ethan Rathbun; Kaleel Mahmood; Sohaib Ahmad; Caiwen Ding; Marten van Dijk; | arxiv-cs.LG | 2022-11-26 |
| 17 | TrustGAN: Training Safe and Trustworthy Deep Learning Models Through Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present here TrustGAN, a generative adversarial network pipeline targeting trustness. |
Hélion du Mas des Bourboux; | arxiv-cs.LG | 2022-11-25 |
| 18 | Learnable Blur Kernel for Single-Image Defocus Deblurring in The Wild Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Moreover, the deblurred image generated by the defocus deblurring network lacks high-frequency details, which is unsatisfactory in human perception. To overcome this issue, we propose a novel defocus deblurring method that uses the guidance of the defocus map to implement image deblurring. |
Jucai Zhai; Pengcheng Zeng; Chihao Ma; Yong Zhao; Jie Chen; | arxiv-cs.CV | 2022-11-25 |
| 19 | Detecting Anomalies Using Generative Adversarial Networks on Images Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a novel Generative Adversarial Network (GAN) based model for anomaly detection. |
Rushikesh Zawar; Krupa Bhayani; Neelanjan Bhowmik; Kamlesh Tiwari; Dhiraj Sangwan; | arxiv-cs.CV | 2022-11-24 |
| 20 | Perception-Oriented Single Image Super-Resolution Using Optimal Objective Estimation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Hence, in this paper, we propose a new SISR framework that applies optimal objectives for each region to generate plausible results in overall areas of high-resolution outputs. |
Seung Ho Park; Young Su Moon; Nam Ik Cho; | arxiv-cs.CV | 2022-11-24 |
| 21 | Dual Graphs of Polyhedral Decompositions for The Detection of Adversarial Attacks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper illustrates how one can utilize the dual graph to detect and analyze adversarial attacks in the context of digital images. |
HUMA JAMIL et. al. | arxiv-cs.CV | 2022-11-23 |
| 22 | GlowGAN: Unsupervised Learning of HDR Images from LDR Images in The Wild Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Despite limited dynamic range, these LDR images are often captured with different exposures, implicitly containing information about the underlying HDR image distribution. Inspired by this intuition, in this work we present, to the best of our knowledge, the first method for learning a generative model of HDR images from in-the-wild LDR image collections in a fully unsupervised manner. |
CHAO WANG et. al. | arxiv-cs.CV | 2022-11-22 |
| 23 | SPIN: Simulated Poisoning and Inversion Network for Federated Learning-Based 6G Vehicular Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose simulated poisoning and inversion network (SPIN) that leverages the optimization approach for reconstructing data from a differential model trained by a vehicular node and intercepted when transmitted to roadside unit (RSU). |
Sunder Ali Khowaja; Parus Khuwaja; Kapal Dev; Angelos Antonopoulos; | arxiv-cs.LG | 2022-11-21 |
| 24 | Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel 3D GAN framework for unsupervised learning of generative, high-quality and 3D-consistent facial avatars from unstructured 2D images. |
JINGXIANG SUN et. al. | arxiv-cs.CV | 2022-11-21 |
| 25 | Spectral Adversarial Training for Robust Graph Neural Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, they are less effective and fraught with challenges on graph data due to the discreteness of graph structure and the relationships between connected examples. In this work, we seek to address these challenges and propose Spectral Adversarial Training (SAT), a simple yet effective adversarial training approach for GNNs. |
JINTANG LI et. al. | arxiv-cs.LG | 2022-11-20 |
| 26 | Towards Adversarial Robustness of Deep Vision Algorithms Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We will discuss the robustness of deep vision algorithms from three perspectives: 1) robustness evaluation (we propose the ObsAtk to evaluate the robustness of denoisers), 2) robustness improvement (HAT, TisODE, and CIFS are developed to robustify vision models), and 3) the connection between adversarial robustness and generalization capability to new domains (we find that adversarially robust denoisers can deal with unseen types of real-world noise). |
Hanshu Yan; | arxiv-cs.LG | 2022-11-19 |
| 27 | Towards Robust Dataset Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, due to the huge computational cost of generating adversarial samples, adversarial training methods are often slow. In this paper, we study the problem of learning a robust dataset such that any classifier naturally trained on the dataset is adversarially robust. |
Yihan Wu; Xinda Li; Florian Kerschbaum; Heng Huang; Hongyang Zhang; | arxiv-cs.CV | 2022-11-19 |
| 28 | Real-World Image Super Resolution Via Unsupervised Bi-directional Cycle Domain Transfer Learning Based Generative Adversarial Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, these deep learning-based super-resolution methods perform poorly in real-world super-resolution tasks, where the paired high-resolution and low-resolution images are unavailable and the low-resolution images are degraded by complicated and unknown kernels. To break these limitations, we propose the Unsupervised Bi-directional Cycle Domain Transfer Learning-based Generative Adversarial Network (UBCDTL-GAN), which consists of an Unsupervised Bi-directional Cycle Domain Transfer Network (UBCDTN) and the Semantic Encoder guided Super Resolution Network (SESRN). |
XIANG WANG et. al. | arxiv-cs.CV | 2022-11-18 |
| 29 | Semantic Encoder Guided Generative Adversarial Face Ultra-Resolution Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Face super-resolution is a domain-specific image super-resolution, which aims to generate High-Resolution (HR) face images from their Low-Resolution (LR) counterparts. In this paper, we propose a novel face super-resolution method, namely Semantic Encoder guided Generative Adversarial Face Ultra-Resolution Network (SEGA-FURN) to ultra-resolve an unaligned tiny LR face image to its HR counterpart with multiple ultra-upscaling factors (e.g., 4x and 8x). |
XIANG WANG et. al. | arxiv-cs.CV | 2022-11-18 |
| 30 | DeepPrivacy2: Towards Realistic Full-Body Anonymization Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel anonymization framework (DeepPrivacy2) for realistic anonymization of human figures and faces. |
Håkon Hukkelås; Frank Lindseth; | arxiv-cs.CV | 2022-11-17 |
| 31 | PointInverter: Point Cloud Reconstruction and Editing Via A Generative Model with Shape Priors Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new method for mapping a 3D point cloud to the latent space of a 3D generative adversarial network. |
Jaeyeon Kim; Binh-Son Hua; Duc Thanh Nguyen; Sai-Kit Yeung; | arxiv-cs.CV | 2022-11-16 |
| 32 | Bayesian Layer Graph Convolutioanl Network for Hyperspetral Image Classification Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we design a Bayesian layer with Bayesian idea as an insertion layer into point estimation based neural networks, and propose a Bayesian Layer Graph Convolutional Network (BLGCN) model by combining graph convolution operations, which can effectively extract graph information and estimate the uncertainty of classification results. |
MINGYANG ZHANG et. al. | arxiv-cs.CV | 2022-11-14 |
| 33 | Row Conditional-TGAN for Generating Synthetic Relational Databases Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose the Row Conditional-Tabular Generative Adversarial Network (RC-TGAN), a novel generative adversarial network (GAN) model that extends the tabular GAN to support modeling and synthesizing relational databases. |
Mohamed Gueye; Yazid Attabi; Maxime Dumas; | arxiv-cs.LG | 2022-11-14 |
| 34 | Shared Loss Between Generators of GANs Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The novelty in this paper lies in making the generators compete against each other while interacting with the discriminator simultaneously. |
Xin Wang; | arxiv-cs.LG | 2022-11-14 |
| 35 | ABCAS: Adaptive Bound Control of Spectral Norm As Automatic Stabilizer Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our method improves the stability of the training of Generative Adversarial Network and achieved better Fr\’echet Inception Distance score of generated images. |
Shota Hirose; Shiori Maki; Naoki Wada; Heming Sun; Jiro Katto; | arxiv-cs.CV | 2022-11-12 |
| 36 | Long-Range Zero-Shot Generative Deep Network Quantization Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We find it is because: 1) a normal generator is hard to obtain high diversity of synthetic data, since it lacks long-range information to allocate attention to global features; 2) the synthetic images aim to simulate the statistics of real data, which leads to weak intra-class heterogeneity and limited feature richness. To overcome these problems, we propose a novel deep network quantizer, dubbed Long-Range Zero-Shot Generative Deep Network Quantization (LRQ). |
YAN LUO et. al. | arxiv-cs.CV | 2022-11-12 |
| 37 | A Generative Approach for Production-Aware Industrial Network Traffic Modeling Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we investigate the network traffic data generated from a laser cutting machine deployed in a Trumpf factory in Germany. |
Alessandro Lieto; Qi Liao; Christian Bauer; | arxiv-cs.LG | 2022-11-11 |
| 38 | GANStrument: Adversarial Instrument Sound Synthesis with Pitch-invariant Instance Conditioning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose GANStrument, a generative adversarial model for instrument sound synthesis. |
Gaku Narita; Junichi Shimizu; Taketo Akama; | arxiv-cs.SD | 2022-11-10 |
| 39 | Test-time Adversarial Detection and Robustness for Localizing Humans Using Ultra Wide Band Channel Impulse Responses Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a test-time adversarial example detector which detects the input adversarial example through quantifying the localized intermediate responses of a pre-trained neural network and confidence scores of an auxiliary softmax layer. |
Abhiram Kolli; Muhammad Jehanzeb Mirza; Horst Possegger; Horst Bischof; | arxiv-cs.LG | 2022-11-10 |
| 40 | Framework Construction of An Adversarial Federated Transfer Learning Classifier Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we offer a novel medical diagnostic framework that employs a federated learning platform to ensure patient data privacy by transferring classification algorithms acquired in a labeled domain to a domain with sparse or missing labeled data. |
Hang Yi; Tongxuan Bie; Tongjiang Yan; | arxiv-cs.LG | 2022-11-09 |
| 41 | NaturalAdversaries: Can Naturalistic Adversaries Be As Effective As Artificial Adversaries? Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce a two-stage adversarial example generation framework (NaturalAdversaries), for designing adversaries that are effective at fooling a given classifier and demonstrate natural-looking failure cases that could plausibly occur during in-the-wild deployment of the models. |
Saadia Gabriel; Hamid Palangi; Yejin Choi; | arxiv-cs.CL | 2022-11-08 |
| 42 | Underwater Image Super-Resolution Using Generative Adversarial Network-based Model Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we fine-tune the Real-Enhanced Super-Resolution Generative Adversarial Network (Real-ESRGAN) model to increase the resolution of underwater images. |
Alireza Aghelan; | arxiv-cs.CV | 2022-11-07 |
| 43 | ABC: Adversarial Behavioral Cloning for Offline Mode-Seeking Imitation Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we describe a key disadvantage of BC that arises due to the maximum likelihood objective function; namely that BC is mean-seeking with respect to the state-conditional expert action distribution when the learner’s policy is represented with a Gaussian. |
Eddy Hudson; Ishan Durugkar; Garrett Warnell; Peter Stone; | arxiv-cs.LG | 2022-11-07 |
| 44 | Are AlphaZero-like Agents Robust to Adversarial Perturbations? Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, searching the adversarial state is challenging due to the large, discrete, and non-differentiable search space. To tackle this challenge, we develop the first adversarial attack on Go AIs that can efficiently search for adversarial states by strategically reducing the search space. |
LI-CHENG LAN et. al. | arxiv-cs.AI | 2022-11-07 |
| 45 | Deviations in Representations Induced By Adversarial Attacks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We present a method for measuring and analyzing the deviations in representations induced by adversarial attacks, progressively across a selected set of layers. |
Daniel Steinberg; Paul Munro; | arxiv-cs.LG | 2022-11-07 |
| 46 | LogiGAN: Learning Logical Reasoning Via Adversarial Pre-training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present LogiGAN, an unsupervised adversarial pre-training framework for improving logical reasoning abilities of language models. |
Xinyu Pi; Wanjun Zhong; Yan Gao; Nan Duan; Jian-Guang Lou; | nips | 2022-11-06 |
| 47 | DASCO: Dual-Generator Adversarial Support Constrained Offline Reinforcement Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, in practice, GAN-based offline RL methods have not outperformed alternative approaches, perhaps because the generator is trained to both fool the discriminator and maximize return – two objectives that are often at odds with each other. In this paper, we show that the issue of conflicting objectives can be resolved by training two generators: one that maximizes return, with the other capturing the remainder of the data distribution in the offline dataset, such that the mixture of the two is close to the behavior policy. |
Quan Vuong; Aviral Kumar; Sergey Levine; Yevgen Chebotar; | nips | 2022-11-06 |
| 48 | Generative Neural Articulated Radiance Fields Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: These 3D GANs, however, have not been demonstrated for human bodies and the generated radiance fields of existing frameworks are not directly editable, limiting their applicability in downstream tasks. We propose a solution to these challenges by developing a 3D GAN framework that learns to generate radiance fields of human bodies or faces in a canonical pose and warp them using an explicit deformation field into a desired body pose or facial expression. |
ALEXANDER BERGMAN et. al. | nips | 2022-11-06 |
| 49 | Unsupervised Point Cloud Completion and Segmentation By Generative Adversarial Autoencoding Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a unsupervised method for point cloud completion and segmentation. |
CHANGFENG MA et. al. | nips | 2022-11-06 |
| 50 | On Translation and Reconstruction Guarantees of The Cycle-Consistent Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The involvement of two unalike data spaces and the existence of multiple solution maps between them are some of the facets that make such architectures unique. In this study, we investigate the statistical properties of such unpaired data translator networks between distinct spaces, bearing the additional responsibility of cycle-consistency. |
Anish Chakrabarty; Swagatam Das; | nips | 2022-11-06 |
| 51 | On The Robustness of Deep Clustering Models: Adversarial Attacks and Defenses Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Through this work, we thus aim to motivate the need for truly robust deep clustering models. |
Anshuman Chhabra; Ashwin Sekhari; Prasant Mohapatra; | nips | 2022-11-06 |
| 52 | GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, there are no existing generative models that show good performance for both types without any model changes. Therefore, we present a general purpose model capable of synthesizing regular and irregular time series data. |
Jinsung Jeon; JEONGHAK KIM; Haryong Song; Seunghyeon Cho; Noseong Park; | nips | 2022-11-06 |
| 53 | GAMA: Generative Adversarial Multi-Object Scene Attacks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Due to their inherent property of strong transferability of perturbations to unknown models, this paper presents the first approach of using generative models for adversarial attacks on multi-object scenes. |
ABHISHEK AICH et. al. | nips | 2022-11-06 |
| 54 | Generalized One-shot Domain Adaption of Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Besides, to realize cross-domain correspondence, we propose the variational Laplacian regularization to constrain the smoothness of the adapted generator. |
ZICHENG ZHANG et. al. | nips | 2022-11-06 |
| 55 | GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In our work, we aim to train performant 3D generative models that synthesize textured meshes which can be directly consumed by 3D rendering engines, thus immediately usable in downstream applications. |
JUN GAO et. al. | nips | 2022-11-06 |
| 56 | Improving Generative Adversarial Networks Via Adversarial Learning in Latent Space Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes to improve the performance of GAN in terms of generative quality and diversity by mining the latent space using adversarial learning. |
Yang Li; Yichuan Mo; Liangliang Shi; Junchi Yan; | nips | 2022-11-06 |
| 57 | Can Push-forward Generative Models Fit Multimodal Distributions? Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Among these models are the Variational Autoencoders and the Generative Adversarial Networks. In this work, we call them "push-forward" models and study their expressivity. |
Antoine Salmona; Valentin De Bortoli; Julie Delon; Agnes Desolneux; | nips | 2022-11-06 |
| 58 | Information-Theoretic Generative Model Compression with Variational Energy-based Model Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an information-theoretic knowledge distillation approach for the compression of generative adversarial networks, which aims to maximize the mutual information between teacher and student networks. |
MINSOO KANG et. al. | nips | 2022-11-06 |
| 59 | Instability and Local Minima in GAN Training with Kernel Discriminators Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Despite their empirical success, the training of GANs is not fully understood due to the joint training of the generator and discriminator. This paper analyzes these joint dynamics when the true samples, as well as the generated samples, are discrete, finite sets, and the discriminator is kernel-based. |
Evan Becker; Parthe Pandit; Sundeep Rangan; Alyson Fletcher; | nips | 2022-11-06 |
| 60 | MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a generative adversarial network with multiple discriminators, which collaborate to represent a real dataset more effectively. |
Jinyoung Choi; Bohyung Han; | nips | 2022-11-06 |
| 61 | Masked Generative Adversarial Networks Are Robust Generation Learners Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper shows that masked generative adversarial network (MaskedGAN) is robust image generation learners with limited training data. |
JIAXING HUANG et. al. | nips | 2022-11-06 |
| 62 | Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We presented a method DiFa to address the diverse generation and faithful adaptation issues for one-shot generative domain adaption. |
YABO ZHANG et. al. | nips | 2022-11-06 |
| 63 | UniGAN: Reducing Mode Collapse in GANs Using A Uniform Generator Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new type of generative diversity named uniform diversity, which relates to a newly proposed type of mode collapse named $u$-mode collapse where the generative samples distribute nonuniformly over the data manifold. |
Ziqi Pan; Li Niu; Liqing Zhang; | nips | 2022-11-06 |
| 64 | Increasing Confidence in Adversarial Robustness Evaluations Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a test that enables researchers to find flawed adversarial robustness evaluations. Passing our test produces compelling evidence that the attacks used have sufficient power to evaluate the model’s robustness. |
Roland S. Zimmermann; Wieland Brendel; Florian Tramer; Nicholas Carlini; | nips | 2022-11-06 |
| 65 | Random Normalization Aggregation for Adversarial Defense Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on our theoretical analysis, we propose a simple yet effective module named Random Normalization Aggregation (RNA) which replaces the batch normalization layers in the networks and aggregates different selected normalization types to form a huge random space. |
Minjing Dong; Xinghao Chen; Yunhe Wang; Chang Xu; | nips | 2022-11-06 |
| 66 | Adversarial Reprogramming Revisited Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We show that neural networks with random weights are susceptible to adversarial reprogramming, and that in some settings training the network can cause its adversarial reprogramming to fail. |
Matthias Englert; Ranko Lazic; | nips | 2022-11-06 |
| 67 | When Adversarial Training Meets Vision Transformers Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper investigates the training techniques and utilizes the unique architectures to improve the adversarial robustness of Vision transformers. |
Yichuan Mo; Dongxian Wu; Yifei Wang; Yiwen Guo; Yisen Wang; | nips | 2022-11-06 |
| 68 | Boosting The Transferability of Adversarial Attacks with Reverse Adversarial Perturbation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Deep neural networks (DNNs) have been shown to be vulnerable to adversarial examples, which can produce erroneous predictions by injecting imperceptible perturbations. In this work, we study the transferability of adversarial examples, which is significant due to its threat to real-world applications where model architecture or parameters are usually unknown. |
ZEYU QIN et. al. | nips | 2022-11-06 |
| 69 | Cooperative Distribution Alignment Via JSD Upper Bound Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We present empirical results of our framework on both simulated and real-world datasets to demonstrate the benefits of our approach. |
Wonwoong Cho; ZIYU GONG; David Inouye; | nips | 2022-11-06 |
| 70 | Adversarial Robustness Is at Odds with Lazy Training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we take one step further and show that one single gradient step can find adversarial examples for networks trained in the so-called lazy regime. |
Yunjuan Wang; Enayat Ullah; Poorya Mianjy; Raman Arora; | nips | 2022-11-06 |
| 71 | Explicit Tradeoffs Between Adversarial and Natural Distributional Robustness Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In practice, however, models need to enjoy both types of robustness to ensure reliability. In this work, we bridge this gap and show that in fact, {\it explicit tradeoffs} exist between adversarial and natural distributional robustness. |
Mazda Moayeri; Kiarash Banihashem; Soheil Feizi; | nips | 2022-11-06 |
| 72 | Your Out-of-Distribution Detection Method Is Not Robust! Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We subsequently propose the Adversarially Trained Discriminator (ATD), which utilizes a pre-trained robust model to extract robust features, and a generator model to create OOD samples. |
MOHAMMAD AZIZMALAYERI et. al. | nips | 2022-11-06 |
| 73 | Evolution of Neural Tangent Kernels Under Benign and Adversarial Training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we perform an empirical study of the evolution of the NTK under standard and adversarial training, aiming to disambiguate the effect of adversarial training on kernel learning and lazy training. |
Noel Loo; Ramin Hasani; Alexander Amini; Daniela Rus; | nips | 2022-11-06 |
| 74 | SNN-RAT: Robustness-enhanced Spiking Neural Network Through Regularized Adversarial Training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Experimental and theoretical insights about the robustness of spiking neural networks motivate a robust training scheme. |
Jianhao Ding; Tong Bu; Zhaofei Yu; Jian Liu; Tiejun Huang; | nips | 2022-11-06 |
| 75 | Gradient Methods Provably Converge to Non-Robust Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we identify natural settings where depth-$2$ ReLU networks trained with gradient flow are provably non-robust (susceptible to small adversarial $\ell_2$-perturbations), even when robust networks that classify the training dataset correctly exist. |
Gal Vardi; Gilad Yehudai; Ohad Shamir; | nips | 2022-11-06 |
| 76 | Data-free Defense of Black Box Models Against Adversarial Attacks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To minimize adversarial contamination on perturbed samples, we propose `wavelet noise remover’ (WNR) that performs discrete wavelet decomposition on input images and carefully select only a few important coefficients determined by our `wavelet coefficient selection module’ (WCSM). |
Gaurav Kumar Nayak; Inder Khatri; Shubham Randive; Ruchit Rawal; Anirban Chakraborty; | arxiv-cs.LG | 2022-11-03 |
| 77 | Physically Adversarial Attacks and Defenses in Computer Vision: A Survey Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we summarize a survey versus the current physically adversarial attacks and physically adversarial defenses in computer vision. |
Xingxing Wei; Bangzheng Pu; Jiefan Lu; Baoyuan Wu; | arxiv-cs.CV | 2022-11-03 |
| 78 | Human Biophysics As Network Weights: Conditional Generative Models for Ultra-fast Simulation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the alternative approach to use conditional generative models, which can learn complex relationships between the underlying generative conditions whilst remaining inexpensive to sample from. |
SHIHAN MA et. al. | arxiv-cs.LG | 2022-11-03 |
| 79 | Comparision Of Adversarial And Non-Adversarial LSTM Music Generative Models Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work implements and compares adversarial and non-adversarial training of recurrent neural network music composers on MIDI data. |
Moseli Mots’oehli; Anna Sergeevna Bosman; Johan Pieter De Villiers; | arxiv-cs.LG | 2022-11-01 |
| 80 | Scoring Black-Box Models for Adversarial Robustness Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a simple scoring method for black-box models which indicates their robustness to adversarial input. |
Jian Vora; Pranay Reddy Samala; | arxiv-cs.LG | 2022-10-31 |
| 81 | Embedding Space Augmentation for Weakly Supervised Learning in Whole-Slide Images Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In most MIL based analytical pipelines for WSI-level analysis, the WSIs are often divided into patches and deep features for patches (i.e., patch embeddings) are extracted prior to training to reduce the overall computational cost and cope with the GPUs’ limited RAM. To overcome this limitation, we present EmbAugmenter, a data augmentation generative adversarial network (DA-GAN) that can synthesize data augmentations in the embedding space rather than in the pixel space, thereby significantly reducing the computational requirements. |
Imaad Zaffar; Guillaume Jaume; Nasir Rajpoot; Faisal Mahmood; | arxiv-cs.CV | 2022-10-30 |
| 82 | Multi-task Generative Adversarial Network for Missing Mobility Data Imputation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a multi-task generative adversarial network, termed as MDI-MG, to mitigate the negative impact of missing mobility data by imputing possible missing records. |
Meihui Shi; Derong Shen; Yue Kou; Tiezheng Nie; Ge Yu; | cikm | 2022-10-29 |
| 83 | Generative Adversarial Zero-Shot Learning for Cold-Start News Recommendation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we utilize the generative adversarial zero-shot learning in building a framework, namely, GAZRec, which is able to address the CSP caused by purely new users or new news. |
Manal A. Alshehri; Xiangliang Zhang; | cikm | 2022-10-29 |
| 84 | Context-aware Traffic Flow Forecasting in New Roads Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel prediction model based on Generative Adversarial Networks (GAN) that learns the subtle patterns of the changes in the traffic flow according to the various contextual factors. |
NAMHYUK KIM et. al. | cikm | 2022-10-29 |
| 85 | Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting Across Cities Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To this end, this paper aims to propose a novel transferable traffic forecasting framework: Domain Adversarial Spatial-Temporal Network (DASTNet). |
YIHONG TANG et. al. | cikm | 2022-10-29 |
| 86 | Adversarial Robustness Through Bias Variance Decomposition: A New Perspective for Federated Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Federated learning learns a neural network model by aggregating the knowledge from a group of distributed clients under the privacy-preserving constraint. In this work, we show that this paradigm might inherit the adversarial vulnerability of the centralized neural network, i.e., it has deteriorated performance on adversarial examples when the model is deployed. |
Yao Zhou; Jun Wu; Haixun Wang; Jingrui He; | cikm | 2022-10-29 |
| 87 | Anomaly Detection in Additive Manufacturing Processes Using Supervised Classification with Imbalanced Sensor Data Based on Generative Adversarial Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: It is beneficial to generate effective artificial sample data for the abnormal states to make a more balanced training set. To achieve this goal, this paper proposes a novel data augmentation method based on a generative adversarial network (GAN) using additive manufacturing process image sensor data. |
Jihoon Chung; Bo Shen; Zhenyu; Kong; | arxiv-cs.LG | 2022-10-28 |
| 88 | Improving Hyperspectral Adversarial Robustness Using Ensemble Networks in The Presences of Multiple Attacks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Traditional approaches to adversarial robustness focus on training or retraining a single network on attacked data, however, in the presence of multiple attacks these approaches decrease the performance compared to networks trained individually on each attack. To combat this issue we propose an Adversarial Discriminator Ensemble Network (ADE-Net) which focuses on attack type detection and adversarial robustness under a unified model to preserve per data-type weight optimally while robustifiying the overall network. |
Nicholas Soucy; Salimeh Yasaei Sekeh; | arxiv-cs.LG | 2022-10-28 |
| 89 | SAN: A Robust End-to-end ASR Model Architecture Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel Siamese Adversarial Network (SAN) architecture for automatic speech recognition, which aims at solving the difficulty of fuzzy audio recognition. |
Zeping Min; Qian Ge; Guanhua Huang; | arxiv-cs.SD | 2022-10-27 |
| 90 | Deep Generative Models on 3D Representations: A Survey Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this survey, we make a thorough review of the development of 3D generation, including 3D shape generation and 3D-aware image synthesis, from the perspectives of both algorithms and more importantly representations. |
Zifan Shi; Sida Peng; Yinghao Xu; Yiyi Liao; Yujun Shen; | arxiv-cs.CV | 2022-10-27 |
| 91 | Articulation GAN: Unsupervised Modeling of Articulatory Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We propose a new unsupervised generative model of speech production/synthesis that includes articulatory representations and thus more closely mimics human speech production. |
Gašper Beguš; Alan Zhou; Peter Wu; Gopala K Anumanchipalli; | arxiv-cs.SD | 2022-10-27 |
| 92 | LeNo: Adversarial Robust Salient Object Detection Networks with Learnable Noise Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Different from ROSA that rely on various pre- and post-processings, this paper proposes a light-weight Learnble Noise (LeNo) to against adversarial attacks for SOD models. |
He Tang; He Wang; | arxiv-cs.CV | 2022-10-27 |
| 93 | TAD: Transfer Learning-based Multi-Adversarial Detection of Evasion Attacks Against Network Intrusion Detection Systems Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The objective of this paper is to design an efficient transfer learning-based adversarial detector and then to assess the effectiveness of using multiple strategically placed adversarial detectors compared to a single adversarial detector for intrusion detection systems. |
ISLAM DEBICHA et. al. | arxiv-cs.CR | 2022-10-27 |
| 94 | SCP-GAN: Self-Correcting Discriminator Optimization for Training Consistency Preserving Metric GAN on Speech Enhancement Tasks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce several improvements to the GAN training schemes, which can be applied to most GAN-based SE models. |
Vasily Zadorozhnyy; Qiang Ye; Kazuhito Koishida; | arxiv-cs.SD | 2022-10-26 |
| 95 | Improving Adversarial Robustness with Self-Paced Hard-Class Pair Reweighting Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we propose to upweight hard-class pair losses in model optimization, which prompts learning discriminative features from hard classes. |
Pengyue Hou; Jie Han; Xingyu Li; | arxiv-cs.CV | 2022-10-26 |
| 96 | Modeling The Graphotactics of Low-Resource Languages Using Sequential GANs Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper will discuss the implementation and testing of a GAN that attempts to model and reproduce the graphotactics of a language using only 100 example strings. |
Isaac Wasserman; | arxiv-cs.CL | 2022-10-25 |
| 97 | Zero-Shot Learning of A Conditional Generative Adversarial Network for Data-Free Network Quantization Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel method for training a conditional generative adversarial network (CGAN) without the use of training data, called zero-shot learning of a CGAN (ZS-CGAN). |
Yoojin Choi; Mostafa El-Khamy; Jungwon Lee; | arxiv-cs.CV | 2022-10-25 |
| 98 | Adversarially Robust Medical Classification Via Attentive Convolutional Neural Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents the inclusion of attention mechanisms in CNN-based medical image classifiers as a reliable and effective strategy for increasing robust accuracy without sacrifice. |
Isaac Wasserman; | arxiv-cs.CV | 2022-10-25 |
| 99 | Imbalanced Class Data Performance Evaluation and Improvement Using Novel Generative Adversarial Network-based Approach: SSG and GBO Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This study proposes two novel techniques: GAN-based Oversampling (GBO) and Support Vector Machine-SMOTE-GAN (SSG) to overcome the limitations of the existing oversampling approaches. |
Md Manjurul Ahsan; Md Shahin Ali; Zahed Siddique; | arxiv-cs.LG | 2022-10-23 |
| 100 | Efficient Hair Style Transfer with Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The current state-of-the-art hair synthesis approaches struggle to maintain global composition of the target style and cannot be used in real-time applications due to their high running costs on high-resolution portrait images. Therefore, We propose a novel hairstyle transfer method, called EHGAN, which reduces computational costs to enable real-time processing while improving the transfer of hairstyle with better global structure compared to the other state-of-the-art hair synthesis methods. |
Muhammed Pektas; Baris Gecer; Aybars Ugur; | arxiv-cs.CV | 2022-10-22 |
| 101 | Generative Range Imaging for Learning Scene Priors of 3D LiDAR Data Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To address the issue, this paper proposes a generative model of LiDAR range images applicable to the data-level domain transfer. |
Kazuto Nakashima; Yumi Iwashita; Ryo Kurazume; | arxiv-cs.CV | 2022-10-21 |
| 102 | PalGAN: Image Colorization with Palette Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Multimodal ambiguity and color bleeding remain challenging in colorization. To tackle these problems, we propose a new GAN-based colorization approach PalGAN, integrated with palette estimation and chromatic attention. |
Yi Wang; Menghan Xia; Lu Qi; Jing Shao; Yu Qiao; | arxiv-cs.CV | 2022-10-20 |
| 103 | Robust One-Shot Singing Voice Conversion Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, it is often difficult to collect them in advance and singing voices are often distorted with reverb and accompaniment music. In this work, we propose robust one-shot SVC (ROSVC) that performs any-to-any SVC robustly even on such distorted singing voices using less than 10s of a reference voice. |
Naoya Takahashi; Mayank Kumar Singh; Yuki Mitsufuji; | arxiv-cs.SD | 2022-10-20 |
| 104 | Learning Sample Reweighting for Accuracy and Adversarial Robustness Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel adversarial training framework that learns to reweight the loss associated with individual training samples based on a notion of class-conditioned margin, with the goal of improving robust generalization. |
Chester Holtz; Tsui-Wei Weng; Gal Mishne; | arxiv-cs.LG | 2022-10-20 |
| 105 | K-SALSA: K-Anonymous Synthetic Averaging of Retinal Images Via Local Style Alignment Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: While prior works have explored image de-identification strategies based on synthetic averaging of images in other domains (e.g. facial images), existing techniques face difficulty in preserving both privacy and clinical utility in retinal images, as we demonstrate in our work. We therefore introduce k-SALSA, a generative adversarial network (GAN)-based framework for synthesizing retinal fundus images that summarize a given private dataset while satisfying the privacy notion of k-anonymity. |
Minkyu Jeon; Hyeonjin Park; Hyunwoo J. Kim; Michael Morley; Hyunghoon Cho; | eccv | 2022-10-19 |
| 106 | Generative Adversarial Network for Future Hand Segmentation from Egocentric Video Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We introduce the novel problem of anticipating a time series of future hand masks from egocentric video. |
Wenqi Jia; Miao Liu; James M. Rehg; | eccv | 2022-10-19 |
| 107 | ChunkyGAN: Real Image Inversion Via Segments Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present ChunkyGAN-a novel paradigm for modeling and editing images using generative adversarial networks. |
LA ŠUBRTOV&AACUTE AD&EACUTE et. al. | eccv | 2022-10-19 |
| 108 | Backdoor Attack and Defense in Federated Generative Adversarial Network-based Medical Image Synthesis Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate the overlooked issue of backdoor attacks in federated GANs (FedGANs). |
Ruinan Jin; Xiaoxiao Li; | arxiv-cs.CV | 2022-10-19 |
| 109 | Temporally Consistent Semantic Video Editing Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a simple yet effective method to facilitate temporally coherent video editing. |
Yiran Xu; Badour AlBahar; Jia-Bin Huang; | eccv | 2022-10-19 |
| 110 | Neural Video Compression Using GANs for Detail Synthesis and Propagation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present the first neural video compression method based on generative adversarial networks (GANs). |
FABIAN MENTZER et. al. | eccv | 2022-10-19 |
| 111 | Difficulty-Aware Simulator for Open Set Recognition Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Therefore, we present a novel framework, DIfficulty-Aware Simulator (DIAS), that generates fakes with diverse difficulty levels to simulate the real world. |
WonJun Moon; Junho Park; Hyun Seok Seong; Cheol-Ho Cho; Jae-Pil Heo; | eccv | 2022-10-19 |
| 112 | Generative Meta-Adversarial Network for Unseen Object Navigation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on the problem of navigating to unseen objects in new environments only based on limited training knowledge. |
Sixian Zhang; Weijie Li; Xinhang Song; Yubing Bai; Shuqiang Jiang; | eccv | 2022-10-19 |
| 113 | DeltaGAN: Towards Diverse Few-Shot Image Generation with Sample-Specific Delta Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we propose a novel Delta Generative Adversarial Network (DeltaGAN), which consists of a reconstruction subnetwork and a generation subnetwork. |
Yan Hong; Li Niu; Jianfu Zhang; Liqing Zhang; | eccv | 2022-10-19 |
| 114 | Adaptive Feature Interpolation for Low-Shot Image Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Training of generative models especially Generative Adversarial Networks can easily diverge in low-data setting. To mitigate this issue, we propose a novel implicit data augmentation approach which facilitates stable training and synthesize high-quality samples without need of label information. |
Mengyu Dai; Haibin Hang; Xiaoyang Guo; | eccv | 2022-10-19 |
| 115 | Robust Network Architecture Search Via Feature Distortion Restraining Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Robust Network Architecture Search (RNAS) to obtain a robust network against adversarial attacks. |
YAGUAN QIAN et. al. | eccv | 2022-10-19 |
| 116 | Model-Free Prediction of Adversarial Drop Points in 3D Point Clouds Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Generally, methods for identifying adversarial points rely on the deep model itself in order to determine which points are critically important for the model’s decision. This paper aims to provide a novel viewpoint on this problem, in which adversarial points can be predicted independently of the model. |
Hanieh Naderi; Chinthaka Dinesh; Ivan V. Bajic; Shohreh Kasaei; | arxiv-cs.CV | 2022-10-19 |
| 117 | Learning Energy-Based Models with Adversarial Training Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We study a new approach to learning energy-based models (EBMs) based on adversarial training (AT). |
Xuwang Yin; Shiying Li; Gustavo K. Rohde; | eccv | 2022-10-19 |
| 118 | $\ell_\infty$-Robustness and Beyond: Unleashing Efficient Adversarial Training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, by leveraging the theory of coreset selection, we show how selecting a small subset of training data provides a general, more principled approach toward reducing the time complexity of robust training. |
Hadi M. Dolatabadi; Sarah Erfani; Christopher Leckie; | eccv | 2022-10-19 |
| 119 | Boosting Transferability of Targeted Adversarial Examples Via Hierarchical Generative Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To this end, we develop a simple yet effective framework to craft targeted transfer-based adversarial examples, applying a hierarchical generative network. |
Xiao Yang; Yinpeng Dong; Tianyu Pang; Hang Su; Jun Zhu; | eccv | 2022-10-19 |
| 120 | Few-shot Transferable Robust Representation Learning Via Bilevel Attacks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Further, learning transferable robust representations for unseen domains is a difficult problem even with a large amount of data. To tackle such a challenge, we propose a novel adversarial self-supervised meta-learning framework with bilevel attacks which aims to learn robust representations that can generalize across tasks and domains. |
Minseon Kim; Hyeonjeong Ha; Sung Ju Hwang; | arxiv-cs.LG | 2022-10-19 |
| 121 | Scaling Adversarial Training to Large Perturbation Bounds Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we aim to achieve adversarial robustness within larger bounds, against perturbations that may be perceptible, but do not change human (or Oracle) prediction. |
Sravanti Addepalli; Samyak Jain; Gaurang Sriramanan; R. Venkatesh Babu; | eccv | 2022-10-19 |
| 122 | Enhanced Accuracy and Robustness Via Multi-Teacher Adversarial Distillation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To improve the robust and clean accuracy of small models, we introduce the Multi-Teacher Adversarial Robustness Distillation (MTARD) to guide the adversarial training process of small models. |
Shiji Zhao; Jie Yu; Zhenlong Sun; Bo Zhang; Xingxing Wei; | eccv | 2022-10-19 |
| 123 | Towards Efficient Adversarial Training on Vision Transformers Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we first comprehensively study fast adversarial training on a variety of vision transformers and illustrate the relationship between the efficiency and robustness. Then, to expediate adversarial training on ViTs, we propose an efficient Attention Guided Adversarial Training mechanism. |
BOXI WU et. al. | eccv | 2022-10-19 |
| 124 | One Size Does NOT Fit All: Data-Adaptive Adversarial Training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we argue that, for the attackable examples, traditional adversarial training which utilizes a fixed size perturbation ball can create adversarial examples that deviate far away from the original class towards the target class. |
Shuo Yang; Chang Xu; | eccv | 2022-10-19 |
| 125 | SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an effective and efficient segmentation attack method, dubbed SegPGD. |
Jindong Gu; Hengshuang Zhao; Volker Tresp; Philip H. S. Torr; | eccv | 2022-10-19 |
| 126 | On The Robustness of Quality Measures for GANs Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This work evaluates the robustness of quality measures of generative models such as Inception Score (IS) and Fréchet Inception Distance (FID). |
MOTASEM ALFARRA et. al. | eccv | 2022-10-19 |
| 127 | Speaker- and Age-Invariant Training for Child Acoustic Modeling Using Adversarial Multi-Task Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a speaker- and age-invariant training approach based on adversarial multi-task learning is proposed. |
Mostafa Shahin; Beena Ahmed; Julien Epps; | arxiv-cs.SD | 2022-10-18 |
| 128 | Improving Adversarial Robustness By Contrastive Guided Diffusion Process Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thus, we propose the Contrastive-Guided Diffusion Process (Contrastive-DP), which adopts the contrastive loss to guide the diffusion model in data generation. |
Yidong Ouyang; Liyan Xie; Guang Cheng; | arxiv-cs.LG | 2022-10-18 |
| 129 | Probabilistic Categorical Adversarial Attack & Adversarial Training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This also limits the development of adversarial training and potential defenses for categorical data. To tackle this problem, we propose Probabilistic Categorical Adversarial Attack (PCAA), which transfers the discrete optimization problem to a continuous problem that can be solved efficiently by Projected Gradient Descent. |
PENGFEI HE et. al. | arxiv-cs.LG | 2022-10-17 |
| 130 | Nowhere to Hide: A Lightweight Unsupervised Detector Against Adversarial Examples Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an AutoEncoder-based Adversarial Examples (AEAE) detector, that can guard DNN models by detecting adversarial examples with low computation in an unsupervised manner. |
Hui Liu; Bo Zhao; Kehuan Zhang; Peng Liu; | arxiv-cs.LG | 2022-10-16 |
| 131 | Generative Adversarial Learning for Trusted and Secure Clustering in Industrial Wireless Sensor Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, the scale of training dataset can significantly affect the security performances of the systems, while it is a great challenge to detect malicious nodes due to the absence of labeled data regarding novel attacks. To address this issue, this paper presents a generative adversarial network (GAN) based trust management mechanism for Industrial Wireless Sensor Networks (IWSNs). |
Liu Yang; Simon X. Yang; Yun Li; Yinzhi Lu; Tan Guo; | arxiv-cs.NI | 2022-10-14 |
| 132 | Dynamics-aware Adversarial Attack of Adaptive Neural Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we investigate the dynamics-aware adversarial attack problem of adaptive neural networks. |
An Tao; Yueqi Duan; Yingqi Wang; Jiwen Lu; Jie Zhou; | arxiv-cs.CV | 2022-10-14 |
| 133 | When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we provide the first and comprehensive study on the adversarial training recipe of ViTs via extensive evaluation of various training techniques across benchmark datasets. |
Yichuan Mo; Dongxian Wu; Yifei Wang; Yiwen Guo; Yisen Wang; | arxiv-cs.CV | 2022-10-14 |
| 134 | HoechstGAN: Virtual Lymphocyte Staining Using Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We present a framework to virtually stain Hoechst images (which are cheap and widespread) with both CD3 and CD8 to identify T cell subtypes in clear cell renal cell carcinoma using generative adversarial networks. |
Georg Wölflein; In Hwa Um; David J Harrison; Ognjen Arandjelović; | arxiv-cs.CV | 2022-10-13 |
| 135 | Federated Learning for Tabular Data: Exploring Potential Risk to Privacy Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We implement our attack model in a recently developed generic FL software framework for tabular data processing. |
Han Wu; Zilong Zhao; Lydia Y. Chen; Aad van Moorsel; | arxiv-cs.CR | 2022-10-13 |
| 136 | Two Approaches to Inpainting Microstructure with Deep Convolutional Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper we introduce two methods that use generative adversarial networks to generate contiguous inpainted regions of arbitrary shape and size by learning the microstructural distribution from the unoccluded data. |
Isaac Squires; Samuel J. Cooper; Amir Dahari; Steve Kench; | arxiv-cs.CV | 2022-10-13 |
| 137 | Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacy Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: One of the challenges in this context is to create non-existent voices that sound as natural as possible. In this work, we propose to tackle this issue by generating speaker embeddings using a generative adversarial network with Wasserstein distance as cost function. |
SARINA MEYER et. al. | arxiv-cs.SD | 2022-10-13 |
| 138 | AccelAT: A Framework for Accelerating The Adversarial Training of Deep Neural Networks Through Accuracy Gradient Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper aims at accelerating the adversarial training to enable fast development of robust DNN models against adversarial attacks. |
Farzad Nikfam; Alberto Marchisio; Maurizio Martina; Muhammad Shafique; | arxiv-cs.LG | 2022-10-13 |
| 139 | Language Models Are Realistic Tabular Data Generators Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To this end, we propose GReaT (Generation of Realistic Tabular data), which exploits an auto-regressive generative LLM to sample synthetic and yet highly realistic tabular data. |
Vadim Borisov; Kathrin Seßler; Tobias Leemann; Martin Pawelczyk; Gjergji Kasneci; | arxiv-cs.LG | 2022-10-12 |
| 140 | Generative Adversarial Nets: Can We Generate A New Dataset Based on Only One Training Set? Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim to generate a new dataset that has a different distribution from the training set. |
Lan V. Truong; | arxiv-cs.LG | 2022-10-12 |
| 141 | FCT-GAN: Enhancing Table Synthesis Via Fourier Transform Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: While convolution neural networks are shown to be a better architecture than fully connected networks for tabular data synthesizing, two key properties of tabular data are overlooked: (i) the global correlation across columns, and (ii) invariant synthesizing to column permutations of input data. To address the above problems, we propose a Fourier conditional tabular generative adversarial network (FCT-GAN). |
Zilong Zhao; Robert Birke; Lydia Y. Chen; | arxiv-cs.LG | 2022-10-12 |
| 142 | Anomaly Detection Using Generative Models and Sum-Product Networks in Mammography Scans Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel combination of generative models and a probabilistic graphical model. |
MARC DIETRICHSTEIN et. al. | arxiv-cs.CV | 2022-10-12 |
| 143 | GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion Models Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We propose AudioStyleGAN (ASGAN), a new generative adversarial network (GAN) for unconditional speech synthesis. |
Matthew Baas; Herman Kamper; | arxiv-cs.SD | 2022-10-11 |
| 144 | Cross-modal Search Method of Technology Video Based on Adversarial Learning and Feature Fusion Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In cross-modal information search, the data features of different modalities cannot be compared directly, so the semantic gap between different modalities is a key problem that needs to be solved. To address the above problems, this paper proposes a novel Feature Fusion based Adversarial Cross-modal Retrieval method (FFACR) to achieve text-to-video matching, ranking and searching. |
Xiangbin Liu; Junping Du; Meiyu Liang; Ang Li; | arxiv-cs.IR | 2022-10-11 |
| 145 | ConchShell: A Generative Adversarial Networks That Turns Pictures Into Piano Music Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present ConchShell, a multi-modal generative adversarial framework that takes pictures as input to the network and generates piano music samples that match the picture context. |
Wanpeng Fan; Yuanzhi Su; Yuxin Huang; | arxiv-cs.SD | 2022-10-10 |
| 146 | Universal Adversarial Perturbations: Efficiency on A Small Image Dataset Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper we will try to reproduce the experience of the Universal Adversarial Perturbations paper, but on a smaller neural network architecture and training set, in order to be able to study the efficiency of the computed perturbation. |
Waris Radji; | arxiv-cs.CV | 2022-10-10 |
| 147 | Boosting Adversarial Robustness From The Perspective of Effective Margin Regularization Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To maximize the effective margins and learn a robust DNN, we propose to regularize the effective weight norm during training. |
Ziquan Liu; Antoni B. Chan; | arxiv-cs.LG | 2022-10-10 |
| 148 | Revisiting Adapters with Adversarial Training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We establish that using the classification token of a Vision Transformer (ViT) as an adapter is enough to match the classification performance of dual normalization layers, while using significantly less additional parameters. |
Sylvestre-Alvise Rebuffi; Francesco Croce; Sven Gowal; | arxiv-cs.CV | 2022-10-10 |
| 149 | CoopHash: Cooperative Learning of Multipurpose Descriptor and Contrastive Pair Generator Via Variational MCMC Teaching for Supervised Image Hashing Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This limitation results in sub-optimal retrieval performance. To overcome this limitation, we propose a novel framework, the generative cooperative hashing network (CoopHash), which is based on the energy-based cooperative learning. |
Khoa D. Doan; Jianwen Xie; Yaxuan Zhu; Yang Zhao; Ping Li; | arxiv-cs.CV | 2022-10-09 |
| 150 | Pruning Adversarially Robust Neural Networks Without Adversarial Examples Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we propose a novel framework to prune a previously trained robust neural network while maintaining adversarial robustness, without further generating adversarial examples. |
Tong Jian; Zifeng Wang; Yanzhi Wang; Jennifer Dy; Stratis Ioannidis; | arxiv-cs.LG | 2022-10-09 |
| 151 | Dual Pyramid Generative Adversarial Networks for Semantic Image Synthesis Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In particular, small objects tend to fade away and large objects are often generated as collages of patches. In order to address this issue, we propose a Dual Pyramid Generative Adversarial Network (DP-GAN) that learns the conditioning of spatially-adaptive normalization blocks at all scales jointly, such that scale information is bi-directionally used, and it unifies supervision at different scales. |
Shijie Li; Ming-Ming Cheng; Juergen Gall; | arxiv-cs.CV | 2022-10-08 |
| 152 | Flow-based GAN for 3D Point Cloud Generation from A Single Image Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To reconstruct the whole 3D shape of the object shown in the image, the existing deep learning based approaches use either explicit or implicit generative modeling of point clouds, which, however, suffer from limited quality. In this work, we aim to alleviate this issue by introducing a hybrid explicit-implicit generative modeling scheme, which inherits the flow-based explicit generative models for sampling point clouds with arbitrary resolutions while improving the detailed 3D structures of point clouds by leveraging the implicit generative adversarial networks (GANs). |
Yao Wei; George Vosselman; Michael Ying Yang; | arxiv-cs.CV | 2022-10-08 |
| 153 | Practical GAN-based Synthetic IP Header Trace Generation Using NetShare Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We explore the feasibility of using Generative Adversarial Networks (GANs) to automatically learn generative models to generate synthetic packet- and flow header traces for networking tasks (e.g., telemetry, anomaly detection, provisioning). |
Yucheng Yin; Zinan Lin; Minhao Jin; Giulia Fanti; Vyas Sekar; | sigcomm | 2022-10-08 |
| 154 | FedDef: Defense Against Gradient Leakage in Federated Learning-based Network Intrusion Detection Systems Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, it has not yet been systematically evaluated how robust FL-based NIDSs are against existing privacy attacks under existing defenses. To address this issue, we propose two privacy evaluation metrics designed for FL-based NIDSs, including (1) privacy score that evaluates the similarity between the original and recovered traffic features using reconstruction attacks, and (2) evasion rate against NIDSs using Generative Adversarial Network-based adversarial attack with the reconstructed benign traffic. |
Jiahui Chen; Yi Zhao; Qi Li; Xuewei Feng; Ke Xu; | arxiv-cs.CR | 2022-10-08 |
| 155 | Symmetry Subgroup Defense Against Adversarial Attacks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Might the CNN lack of invariance revert symmetrically transformed adversarial samples to the correct classification? This paper answers this question affirmatively for a threat model that ranges from zero-knowledge adversaries to perfect-knowledge adversaries. |
Blerta Lindqvist; | arxiv-cs.LG | 2022-10-08 |
| 156 | Evaluating The Performance of StyleGAN2-ADA on Medical Images Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Although generative adversarial networks (GANs) have shown promise in medical imaging, they have four main limitations that impeded their utility: computational cost, data requirements, reliable evaluation measures, and training complexity. Our work investigates each of these obstacles in a novel application of StyleGAN2-ADA to high-resolution medical imaging datasets. |
MCKELL WOODLAND et. al. | arxiv-cs.CV | 2022-10-07 |
| 157 | Adversarially Robust Prototypical Few-shot Segmentation with Neural-ODEs Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This is even more severe in the case of FSL due to the lack of a large number of training examples. In this paper, we provide a framework to make few-shot segmentation models adversarially robust in the medical domain where such attacks can severely impact the decisions made by clinicians who use them. |
Prashant Pandey; Aleti Vardhan; Mustafa Chasmai; Tanuj Sur; Brejesh Lall; | arxiv-cs.CV | 2022-10-07 |
| 158 | Deep Reinforcement Learning Based Evasion Generative Adversarial Network for Botnet Detection Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, the synthetic evasions may not follow the original semantics of the input samples. This paper proposes a novel GAN model leveraged with deep reinforcement learning (DRL) to explore semantic aware samples and simultaneously harden its detection. |
Rizwan Hamid Randhawa; Nauman Aslam; Mohammad Alauthman; Muhammad Khalid; Husnain Rafiq; | arxiv-cs.CR | 2022-10-06 |
| 159 | Transformer-based Conditional Generative Adversarial Network for Multivariate Time Series Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We use qualitative evaluations and quantitative metrics such as Principal Component Analysis (PCA), and we introduce a modified version of the Frechet inception distance (FID) to measure the performance of our model and the statistical similarities between the generated and the real data distributions. |
ABDELLAH MADANE et. al. | arxiv-cs.LG | 2022-10-05 |
| 160 | Dynamic Stochastic Ensemble with Adversarial Robust Lottery Ticket Subnetworks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the poor adversarial transferability between subnetworks of scratch tickets with various remaining ratios, we propose a method to realize the dynamic stochastic ensemble defense strategy. |
QI PENG et. al. | arxiv-cs.CV | 2022-10-05 |
| 161 | Strength-Adaptive Adversarial Training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Secondly, the attack strength of adversarial training data constrained by the pre-specified perturbation budget fails to upgrade as the growth of network robustness, which leads to robust overfitting and further degrades the adversarial robustness. To overcome these limitations, we propose \emph{Strength-Adaptive Adversarial Training} (SAAT). |
CHAOJIAN YU et. al. | arxiv-cs.LG | 2022-10-03 |
| 162 | ICTGAN–An Attack Mitigation Technique for Random-vector Attack on Accelerometer-based Gait Authentication Systems Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we assess the effectiveness of the random-vector attack on both $v$ABGait and $\beta$ABGait using three accelerometer-based gait datasets. |
Jun Hyung Mo; Rajesh Kumar; | arxiv-cs.CR | 2022-10-02 |
| 163 | Understanding Adversarial Robustness Against On-manifold Adversarial Examples Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we revisit the off-manifold assumption and want to study a question: at what level is the poor performance of neural networks against adversarial attacks due to on-manifold adversarial examples? |
Jiancong Xiao; Liusha Yang; Yanbo Fan; Jue Wang; Zhi-Quan Luo; | arxiv-cs.LG | 2022-10-02 |
| 164 | Evaluation of Pre-Trained CNN Models for Geographic Fake Image Detection Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To advance the field, in this paper, we explore the suitability of several convolutional neural network (CNN) architectures for fake satellite image detection. |
Sid Ahmed Fezza; Mohammed Yasser Ouis; Bachir Kaddar; Wassim Hamidouche; Abdenour Hadid; | arxiv-cs.CV | 2022-10-01 |
| 165 | Your Out-of-Distribution Detection Method Is Not Robust! Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Nevertheless, these efforts remained ineffective, as their evaluations are based on either small perturbation sizes, or weak attacks. In this work, we re-examine these defenses against an end-to-end PGD attack on in/out data with larger perturbation sizes, e.g. up to commonly used $\epsilon=8/255$ for the CIFAR-10 dataset. |
MOHAMMAD AZIZMALAYERI et. al. | arxiv-cs.CV | 2022-09-30 |
| 166 | Cyclegan Network for Sheet Metal Welding Drawing Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes an automatic translation method for welded structural engineering drawings based on Cyclic Generative Adversarial Networks (CycleGAN). |
Zhiwei Song; Hui Yao; Dan Tian; Gaohui Zhan; | arxiv-cs.CV | 2022-09-28 |
| 167 | A Survey on Physical Adversarial Attack in Computer Vision Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we review the development of physical adversarial attacks in DNN-based computer vision tasks, including image recognition tasks, object detection tasks, and semantic segmentation. |
Donghua Wang; Wen Yao; Tingsong Jiang; Guijiang Tang; Xiaoqian Chen; | arxiv-cs.CV | 2022-09-28 |
| 168 | A Comparative Study of Attention Mechanism and Generative Adversarial Network in Facade Damage Segmentation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Attention mechanism and generative adversarial networks are two of the most popular strategies to improve the quality of semantic segmentation. With specific focuses on these two strategies, this paper adopts U-net, a representative convolutional neural network, as the primary network and presents a comparative study in two steps. |
Fangzheng Lin; Jiesheng Yang; Jiangpeng Shu; Raimar J. Scherer; | arxiv-cs.CV | 2022-09-27 |
| 169 | Multi-Task Adversarial Training Algorithm for Multi-Speaker Neural Text-to-Speech Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel training algorithm for a multi-speaker neural text-to-speech (TTS) model based on multi-task adversarial training. |
Yusuke Nakai; Yuki Saito; Kenta Udagawa; Hiroshi Saruwatari; | arxiv-cs.SD | 2022-09-26 |
| 170 | Safety-compliant Generative Adversarial Networks for Human Trajectory Forecasting Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Despite superior performance in reducing distance-based metrics, current networks fail to output socially acceptable trajectories, as evidenced by high collisions in model predictions. To counter this, we introduce SGANv2: an improved safety-compliant SGAN architecture equipped with spatio-temporal interaction modelling and a transformer-based discriminator. |
Parth Kothari; Alexandre Alahi; | arxiv-cs.CV | 2022-09-25 |
| 171 | Controllable Face Manipulation and UV Map Generation By Self-supervised Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we propose to explicitly edit the latent space of the pretrained StyleGAN by controlling the parameters of the 3DMM. |
Yuanming Li; Jeong-gi Kwak; David Han; Hanseok Ko; | arxiv-cs.CV | 2022-09-24 |
| 172 | Goal-Aware Generative Adversarial Imitation Learning from Imperfect Demonstration for Robotic Cloth Manipulation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address this issue by focusing on the following features: 1) many robotic tasks are goal-reaching tasks, and 2) labeling such goal states in demonstration data is relatively easy. With these in mind, this paper proposes Goal-Aware Generative Adversarial Imitation Learning (GA-GAIL), which trains a policy by introducing a second discriminator to distinguish the goal state in parallel with the first discriminator that indicates the demonstration data. |
Yoshihisa Tsurumine; Takamitsu Matsubara; | arxiv-cs.RO | 2022-09-21 |
| 173 | GAMA: Generative Adversarial Multi-Object Scene Attacks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Due to their inherent property of strong transferability of perturbations to unknown models, this paper presents the first approach of using generative models for adversarial attacks on multi-object scenes. |
ABHISHEK AICH et. al. | arxiv-cs.CV | 2022-09-20 |
| 174 | Leveraging Local Patch Differences in Multi-Object Scenes for Generative Adversarial Attacks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Different from such settings, we tackle a more practical problem of generating adversarial perturbations using multi-object (i.e., multiple dominant objects) images as they are representative of most real-world scenes. Our goal is to design an attack strategy that can learn from such natural scenes by leveraging the local patch differences that occur inherently in such images (e.g. difference between the local patch on the object `person’ and the object `bike’ in a traffic scene). |
ABHISHEK AICH et. al. | arxiv-cs.CV | 2022-09-20 |
| 175 | Closing The Gender Wage Gap: Adversarial Fairness in Job Recommendation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: The goal of this work is to help mitigate the already existing gender wage gap by supplying unbiased job recommendations based on resumes from job seekers. |
Clara Rus; Jeffrey Luppes; Harrie Oosterhuis; Gido H. Schoenmacker; | arxiv-cs.LG | 2022-09-20 |
| 176 | Audit and Improve Robustness of Private Neural Networks on Encrypted Data Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This is not a trivial task because the PNet model owner does not have access to the plaintext of the input values, which prevents the application of existing detection and defense methods such as input tuning, model normalization, and adversarial training. To tackle this challenge, we propose a new fast and accurate noise insertion method, called RPNet, to design Robust and Private Neural Networks. |
JIAQI XUE et. al. | arxiv-cs.LG | 2022-09-20 |
| 177 | Encrypted Semantic Communication Using Adversarial Training for Privacy Preserving Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this letter, we propose an encrypted semantic communication system (ESCS) for privacy preserving, which combines universality and confidentiality. |
Xinlai Luo; Zhiyong Chen; Meixia Tao; Feng Yang; | arxiv-cs.IT | 2022-09-19 |
| 178 | On The Adversarial Transferability of ConvMixer Models Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the property of adversarial transferability between models including ConvMixer, which is an isotropic network, for the first time. |
Ryota Iijima; Miki Tanaka; Isao Echizen; Hitoshi Kiya; | arxiv-cs.LG | 2022-09-18 |
| 179 | Versatile Skill Control Via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a cooperative adversarial method for obtaining single versatile policies with controllable skill sets from unlabeled datasets containing diverse state transition patterns by maximizing their discriminability. |
CHENHAO LI et. al. | arxiv-cs.RO | 2022-09-16 |
| 180 | DEQGAN: Learning The Loss Function for PINNs with Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This work presents Differential Equation GAN (DEQGAN), a novel method for solving differential equations using generative adversarial networks to learn the loss function for optimizing the neural network. |
Blake Bullwinkel; Dylan Randle; Pavlos Protopapas; David Sondak; | arxiv-cs.LG | 2022-09-15 |
| 181 | Efficient Low-thrust Trajectory Data Generation Based on Generative Adversarial Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Deep learning-based techniques have been introduced into the field of trajectory optimization in recent years. |
Ruida Xie; Andrew G. Dempster; | arxiv-cs.LG | 2022-09-14 |
| 182 | Learning State Correspondence of Reinforcement Learning Tasks for Knowledge Transfer Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work proposes a general method for one-to-one transfer learning based on generative adversarial network model tailored to RL task. |
Marko Ruman; Tatiana V. Guy; | arxiv-cs.LG | 2022-09-14 |
| 183 | Robust Transferable Feature Extractors: Learning to Defend Pre-Trained Networks Against White Box Adversaries Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a deep learning-based pre-processing mechanism, which we refer to as a robust transferable feature extractor (RTFE). |
Alexander Cann; Ian Colbert; Ihab Amer; | arxiv-cs.LG | 2022-09-14 |
| 184 | Document Image Binarization in JPEG Compressed Domain Using Dual Discriminator Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Most of the existing techniques focus on feeding pixel images into the Convolution Neural Networks to accomplish document binarization, which may not produce effective results when working with compressed images that need to be processed without full decompression. Therefore in this research paper, the idea of document image binarization directly using JPEG compressed stream of document images is proposed by employing Dual Discriminator Generative Adversarial Networks (DD-GANs). |
Bulla Rajesh; Manav Kamlesh Agrawal; Milan Bhuva; Kisalaya Kishore; Mohammed Javed; | arxiv-cs.CV | 2022-09-13 |
| 185 | TSFool: Crafting High-quality Adversarial Time Series Through Multi-objective Optimization to Fool Recurrent Neural Network Classifiers Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, an efficient and widely applicable approach called TSFool for crafting high-quality adversarial time series for the RNN classifier is proposed. |
Yanyun Wang; Dehui Du; Yuanhao Liu; | arxiv-cs.LG | 2022-09-13 |
| 186 | Adversarial Coreset Selection for Efficient Robust Training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In particular, we show that the convergence bound is directly related to how well our coresets can approximate the gradient computed over the entire training data. Motivated by our theoretical analysis, we propose using this gradient approximation error as our adversarial coreset selection objective to reduce the training set size effectively. |
Hadi M. Dolatabadi; Sarah Erfani; Christopher Leckie; | arxiv-cs.LG | 2022-09-13 |
| 187 | Adversarial Inter-Group Link Injection Degrades The Fairness of Graph Neural Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We present evidence for the existence and effectiveness of adversarial attacks on graph neural networks (GNNs) that aim to degrade fairness. |
HUSSAIN HUSSAIN et. al. | arxiv-cs.LG | 2022-09-13 |
| 188 | Vec2Face-v2: Unveil Human Faces from Their Blackbox Features Via Attention-based Network in Face Recognition Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate the problem of face reconstruction given a facial feature representation extracted from a blackbox face recognition engine. |
Thanh-Dat Truong; Chi Nhan Duong; Ngan Le; Marios Savvides; Khoa Luu; | arxiv-cs.CV | 2022-09-11 |
| 189 | Resisting Deep Learning Models Against Adversarial Attack Transferability Via Feature Randomization Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a feature randomization-based approach that resists eight adversarial attacks targeting deep learning models in the testing phase. |
EHSAN NOWROOZI et. al. | arxiv-cs.CR | 2022-09-11 |
| 190 | Diffusion Models in Vision: A Survey Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this survey, we provide a comprehensive review of articles on denoising diffusion models applied in vision, comprising both theoretical and practical contributions in the field. |
Florinel-Alin Croitoru; Vlad Hondru; Radu Tudor Ionescu; Mubarak Shah; | arxiv-cs.CV | 2022-09-10 |
| 191 | Lightweight Long-Range Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce novel lightweight generative adversarial networks, which can effectively capture long-range dependencies in the image generation process, and produce high-quality results with a much simpler architecture. |
Bowen Li; Thomas Lukasiewicz; | arxiv-cs.CV | 2022-09-08 |
| 192 | Generalized One-shot Domain Adaptation of Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we focus on the one-shot case, which is more challenging and rarely explored in previous works. |
ZICHENG ZHANG et. al. | arxiv-cs.CV | 2022-09-08 |
| 193 | Incorporating Locality of Images to Generate Targeted Transferable Adversarial Examples Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we revisit adversarial examples with targeted transferability from the perspective of universality and find that highly universal adversarial perturbations tend to be more transferable. |
Zhipeng Wei; Jingjing Chen; Zuxuan Wu; Yu-Gang Jiang; | arxiv-cs.CV | 2022-09-08 |
| 194 | DC-Art-GAN: Stable Procedural Content Generation Using DC-GANs for Digital Art Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this manuscript, we advocate the concept of using deep generative networks with adversarial training for a stable and variant art generation. |
Rohit Gandikota; Nik Bear Brown; | arxiv-cs.CV | 2022-09-06 |
| 195 | Wavelet-based Loss for High-frequency Interface Dynamics Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: As an alternative, we present a new method based on a wavelet loss formulation, which remains transparent in terms of what is optimized. |
Lukas Prantl; Jan Bender; Tassilo Kugelstadt; Nils Thuerey; | arxiv-cs.LG | 2022-09-06 |
| 196 | Dynamics of Fourier Modes in Torus Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a novel method to analyze the convergence and stability in the training of Generative Adversarial Networks. |
Ángel González-Prieto; Alberto Mozo; Edgar Talavera; Sandra Gómez-Canaval; | arxiv-cs.LG | 2022-09-05 |
| 197 | Exploiting Pre-trained Feature Networks for Generative Adversarial Networks in Audio-domain Loop Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper investigates whether Projected GAN can similarly improve audio generation, by evaluating the performance of a StyleGAN2-based audio-domain loop generation model with and without using a pre-trained feature space in the discriminator. |
Yen-Tung Yeh; Bo-Yu Chen; Yi-Hsuan Yang; | arxiv-cs.SD | 2022-09-05 |
| 198 | Evaluating The Susceptibility of Pre-Trained Language Models Via Handcrafted Adversarial Examples Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Following this approach, we observe a significant decrease in text classification quality when evaluating for semantic similarity. |
HEZEKIAH J. BRANCH et. al. | arxiv-cs.CL | 2022-09-05 |
| 199 | Latent Preserving Generative Adversarial Network for Imbalance Classification Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present an end-to-end deep generative classifier. |
TANMOY DAM et. al. | arxiv-cs.LG | 2022-09-04 |
| 200 | Single-source Domain Expansion Network for Cross-Scene Hyperspectral Image Classification Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The method uses generative adversarial learning to train in SD and test in TD. |
Yuxiang Zhang; Wei Li; Weidong Sun; Ran Tao; Qian Du; | arxiv-cs.CV | 2022-09-04 |
| 201 | DSE-GAN: Dynamic Semantic Evolution Generative Adversarial Network for Text-to-Image Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We thereby propose a novel Dynamical Semantic Evolution GAN (DSE-GAN) to re-compose each stage’s text features under a novel single adversarial multi-stage architecture. |
Mengqi Huang; Zhendong Mao; Penghui Wang; Quan Wang; Yongdong Zhang; | arxiv-cs.CV | 2022-09-03 |
| 202 | Adversarial for Social Privacy: A Poisoning Strategy to Degrade User Identity Linkage Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we reformalize the UIL problem in the perspective of kernelized topology consistency and convert the attack objective to maximizing the structural changes within the target network before and after attacks. |
JIANGLI SHAO et. al. | arxiv-cs.SI | 2022-09-01 |
| 203 | Controllable 3D Generative Adversarial Face Model Via Disentangling Shape and Appearance Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper proposes a new 3D face generative model that can decouple identity and expression and provides granular control over expressions. |
FARIBORZ TAHERKHANI et. al. | arxiv-cs.CV | 2022-08-30 |
| 204 | Massive Data Generation for Deep Learning-aided Wireless Systems Using Meta Learning and Generative Adversarial Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new type of data acquisition framework for DL-aided wireless systems. |
Jinhong Kim; Yongjun Ahn; Byonghyo Shim; | arxiv-cs.IT | 2022-08-25 |
| 205 | Generative Adversarial Network (GAN) Based Image-Deblurring Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Besides, in recent years with the improvement of architectures, the network has been able to output an image closely approximating the ground truth given the blurry observation. The Generative Adversarial Network (GAN) works on this Image-to-Image translation idea. |
Yuhong Lu; Nicholas Polydorides; | arxiv-cs.CV | 2022-08-24 |
| 206 | Trace and Detect Adversarial Attacks on CNNs Using Feature Response Maps Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel detection method for adversarial examples to prevent attacks. |
Mohammadreza Amirian; Friedhelm Schwenker; Thilo Stadelmann; | arxiv-cs.CV | 2022-08-24 |
| 207 | Adversarial Vulnerability of Temporal Feature Networks for Object Detection Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study whether temporal feature networks for object detection are vulnerable to universal adversarial attacks. |
Svetlana Pavlitskaya; Nikolai Polley; Michael Weber; J. Marius Zöllner; | arxiv-cs.CV | 2022-08-23 |
| 208 | Instability and Local Minima in GAN Training with Kernel Discriminators Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Despite their empirical success, the training of GANs is not fully understood due to the min-max optimization of the generator and discriminator. This paper analyzes these joint dynamics when the true samples, as well as the generated samples, are discrete, finite sets, and the discriminator is kernel-based. |
Evan Becker; Parthe Pandit; Sundeep Rangan; Alyson K. Fletcher; | arxiv-cs.LG | 2022-08-21 |
| 209 | Musika! Fast Infinite Waveform Music Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we introduce Musika, a music generation system that can be trained on hundreds of hours of music using a single consumer GPU, and that allows for much faster than real-time generation of music of arbitrary length on a consumer CPU. |
Marco Pasini; Jan Schlüter; | arxiv-cs.SD | 2022-08-18 |
| 210 | Generating Synthetic Clinical Data That Capture Class Imbalanced Distributions with Generative Adversarial Networks: Example Using Antiretroviral Therapy for HIV Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we extend the classic GAN setup with an external memory to replay features from real samples. |
Nicholas I-Hsien Kuo; Louisa Jorm; Sebastiano Barbieri; | arxiv-cs.LG | 2022-08-18 |
| 211 | Two Heads Are Better Than One: Robust Learning Meets Multi-branch Models Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose Branch Orthogonality adveRsarial Training (BORT) to obtain state-of-the-art performance with solely the original dataset for adversarial training. |
DONG HUANG et. al. | arxiv-cs.CV | 2022-08-17 |
| 212 | Interference Cancellation GAN Framework for Dynamic Channels Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce an online training framework that can swiftly adapt to any changes in the channel. |
Hung T. Nguyen; Steven Bottone; Kwang Taik Kim; Mung Chiang; H. Vincent Poor; | arxiv-cs.LG | 2022-08-16 |
| 213 | A New Scheme for Image Compression and Encryption Using ECIES, Henon Map, and AEGAN Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a method for compressing and encryption images is proposed, which can safely transmit images in low-bandwidth data transmission channels. |
Mahdi Shariatzadeh; Mahdi Eftekhari; Mohammad Javad Rostami; | arxiv-cs.MM | 2022-08-16 |
| 214 | Memory-Driven Text-to-Image Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a memory-driven semi-parametric approach to text-to-image generation, which is based on both parametric and non-parametric techniques. |
Bowen Li; Philip H. S. Torr; Thomas Lukasiewicz; | arxiv-cs.CV | 2022-08-15 |
| 215 | Applying Regularized Schrödinger-Bridge-Based Stochastic Process in Generative Modeling Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Compared to the existing function-based models in deep generative modeling, the recently proposed diffusion models have achieved outstanding performance with a stochastic-process-based approach. |
Ki-Ung Song; | arxiv-cs.LG | 2022-08-15 |
| 216 | GNPassGAN: Improved Generative Adversarial Networks For Trawling Offline Password Guessing Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper reviews various deep learning-based password guessing approaches that do not require domain knowledge or assumptions about users’ password structures and combinations. |
Fangyi Yu; Miguel Vargas Martin; | arxiv-cs.CR | 2022-08-14 |
| 217 | Generative Adversarial Networks Enhanced Pre-training for Insufficient Electronic Health Records Modeling Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Directly using them to train sensitive medical models is very difficult to achieve satisfactory results. To overcome this problem, we propose a novel deep model learning method for insufficient EHR (Electronic Health Record) data modeling, namely GRACE, which stands GeneRative Adversarial networks enhanCed prE-training. |
Houxing Ren; Jingyuan Wang; Wayne Xin Zhao; | kdd | 2022-08-12 |
| 218 | SOS: Score-based Oversampling for Tabular Data Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: SGMs are known to surpass other generative models, e.g., generative adversarial networks (GANs) and variational autoencoders (VAEs). Being inspired by their big success, in this work, we fully customize them for generating fake tabular data. |
JAYOUNG KIM et. al. | kdd | 2022-08-12 |
| 219 | MetroGAN: Simulating Urban Morphology with Generative Adversarial Network Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Here, we propose a GAN framework with geographical knowledge, namely Metropolitan GAN (MetroGAN), for urban morphology simulation. |
Weiyu Zhang; Yiyang Ma; Di Zhu; Lei Dong; Yu Liu; | kdd | 2022-08-12 |
| 220 | Scale-free and Task-agnostic Attack: Generating Photo-realistic Adversarial Patterns with Patch Quilting Generator Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel Patch Quilting Generative Adversarial Networks (PQ-GAN) to learn the first scale-free CNN generator that can be applied to attack images with arbitrary scales for various computer vision tasks. |
XIANGBO GAO et. al. | arxiv-cs.CV | 2022-08-12 |
| 221 | Image Translation Based Nuclei Segmentation for Immunohistochemistry Images Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Numerous deep learning based methods have been developed for nuclei segmentation for H&E images and have achieved close to human performance. |
Roger Trullo; Quoc-Anh Bui; Qi Tang; Reza Olfati-Saber; | arxiv-cs.CV | 2022-08-12 |
| 222 | Diverse Generative Perturbations on Attention Space for Transferable Adversarial Attacks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Nevertheless, existing transferable attacks craft perturbations in a deterministic manner and often fail to fully explore the loss surface, thus falling into a poor local optimum and suffering from low transferability. To solve this problem, we propose Attentive-Diversity Attack (ADA), which disrupts diverse salient features in a stochastic manner to improve transferability. |
Woo Jae Kim; Seunghoon Hong; Sung-Eui Yoon; | arxiv-cs.CV | 2022-08-11 |
| 223 | A Sublinear Adversarial Training Algorithm Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we analyze the convergence guarantee of adversarial training procedure on a two-layer neural network with shifted ReLU activation, and shows that only $o(m)$ neurons will be activated for each input data per iteration. |
Yeqi Gao; Lianke Qin; Zhao Song; Yitan Wang; | arxiv-cs.LG | 2022-08-10 |
| 224 | DDSP-based Singing Vocoders: A New Subtractive-based Synthesizer and A Comprehensive Evaluation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Taking inspiration from Differentiable Digital Signal Processing (DDSP), we propose a new vocoder named SawSing for singing voices. |
DA-YI WU et. al. | arxiv-cs.SD | 2022-08-09 |
| 225 | BSDGAN: Balancing Sensor Data Generative Adversarial Networks for Human Activity Recognition Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Balancing Sensor Data Generative Adversarial Networks (BSDGAN) to generate sensor data for minority human activities. |
Yifan Hu; Yu Wang; | arxiv-cs.LG | 2022-08-07 |
| 226 | Dynamic Adaptive and Adversarial Graph Convolutional Network for Traffic Forecasting Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In addition, most approaches individually and independently consider the absolute error between ground truth and predictions at each time step, which fails to maintain the global properties and statistics of time series as a whole and results in trend discrepancy between ground truth and predictions. To this end, in this paper, we propose a Dynamic Adaptive and Adversarial Graph Convolutional Network (DAAGCN), which combines Graph Convolution Networks (GCNs) with Generative Adversarial Networks (GANs) for traffic forecasting. |
Juyong Jiang; Binqing Wu; Ling Chen; Sunghun Kim; | arxiv-cs.LG | 2022-08-05 |
| 227 | Real-time Gesture Animation Generation from Speech for Virtual Human Interaction Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We propose a real-time system for synthesizing gestures directly from speech. |
Manuel Rebol; Christian Gütl; Krzysztof Pietroszek; | arxiv-cs.CV | 2022-08-05 |
| 228 | CIGAN: A Python Package for Handling Class Imbalance Using Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we introduce a software that uses Generative Adversarial Networks to oversample the minority classes so as to improve downstream classification. |
Yuxiao Huang; Yan Ma; | arxiv-cs.LG | 2022-08-04 |
| 229 | Visually Evaluating Generative Adversarial Networks Using Itself Under Multivariate Time Series Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We present a general framework named Gaussian GANs to visually evaluate GANs using itself under the MTS generation task. |
Qilong Pan; | arxiv-cs.LG | 2022-08-04 |
| 230 | Unsupervised Discovery of Semantic Concepts in Satellite Imagery with Style-based Wavelet-driven Generative Models Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In contrast, satellite imagery exhibits great spatial and spectral variability, wide presence of fine, high-frequency details, while the tedious nature of annotating satellite imagery leads to annotation scarcity – further motivating developments in unsupervised learning. In this light, we present the first pre-trained style- and wavelet-based GAN model that can readily synthesize a wide gamut of realistic satellite images in a variety of settings and conditions – while also preserving high-frequency information. |
Nikos Kostagiolas; Mihalis A. Nicolaou; Yannis Panagakis; | arxiv-cs.CV | 2022-08-03 |
| 231 | Explicit Use of Fourier Spectrum in Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate the possible reasons for the mentioned drawback in the architecture and mathematical theory of the current GANs. |
Soroush Sheikh Gargar; | arxiv-cs.CV | 2022-08-02 |
| 232 | Learning to Incorporate Texture Saliency Adaptive Attention to Image Cartoonization Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Existing advanced models try to enhance cartoonization effect by learning to promote edges adversarially, introducing style transfer loss, or learning to align style from multiple representation space. |
Xiang Gao; Yuqi Zhang; Yingjie Tian; | arxiv-cs.CV | 2022-08-02 |
| 233 | GANDSE: Generative Adversarial Network Based Design Space Exploration for Neural Network Accelerator Design Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a neural network accelerator design automation framework named GANDSE, where we rethink the problem of design space exploration, and propose a novel approach based on the generative adversarial network (GAN) to support an optimized exploration for high dimension large design space. |
LANG FENG et. al. | arxiv-cs.LG | 2022-08-01 |
| 234 | Generative Adversarial Learning for Intelligent Trust Management in 6G Wireless Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this article, a generative adversarial learning-enabled trust management method is presented for 6G wireless networks. |
LIU YANG et. al. | arxiv-cs.NI | 2022-08-01 |
| 235 | Generative Bias for Visual Question Answering Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast, in this work, in order to better learn the bias a target VQA model suffers from, we propose a generative method to train the bias model \emph{directly from the target model}, called GenB. |
Jae Won Cho; Dong-jin Kim; Hyeonggon Ryu; In So Kweon; | arxiv-cs.CV | 2022-08-01 |
| 236 | Robust Real-World Image Super-Resolution Against Adversarial Attacks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a robust deep learning framework for real-world SR that randomly erases potential adversarial noises in the frequency domain of input images or features. |
Jiutao Yue; Haofeng Li; Pengxu Wei; Guanbin Li; Liang Lin; | arxiv-cs.CV | 2022-07-31 |
| 237 | GLEAN: Generative Latent Bank for Image Super-Resolution and Beyond Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We extend our method to different tasks including image colorization and blind image restoration, and extensive experiments show that our proposed models perform favorably in comparison to existing methods. |
Kelvin C. K. Chan; Xiangyu Xu; Xintao Wang; Jinwei Gu; Chen Change Loy; | arxiv-cs.CV | 2022-07-29 |
| 238 | Robust Trajectory Prediction Against Adversarial Attacks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we identify two key ingredients to defend trajectory prediction models against adversarial attacks including (1) designing effective adversarial training methods and (2) adding domain-specific data augmentation to mitigate the performance degradation on clean data. |
YULONG CAO et. al. | arxiv-cs.LG | 2022-07-29 |
| 239 | Random Walks for Adversarial Meshes Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper proposes a novel, unified, and general adversarial attack, which leads to misclassification of several state-of-the-art mesh classification neural networks. |
Amir Belder; Gal Yefet; Ran Ben-Itzhak; Ayellet Tal; | siggraph | 2022-07-28 |
| 240 | Generative Steganography Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an advanced generative steganography network (GSN) that can generate realistic stego images without using cover images. |
PING WEI et. al. | arxiv-cs.CV | 2022-07-27 |
| 241 | Stable Parallel Training of Wasserstein Conditional Generative Adversarial Neural Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a stable, parallel approach to train Wasserstein Conditional Generative Adversarial Neural Networks (W-CGANs) under the constraint of a fixed computational budget. |
Massimiliano Lupo Pasini; Junqi Yin; | arxiv-cs.AI | 2022-07-25 |
| 242 | Improving Adversarial Robustness Via Mutual Information Estimation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: They are typically misled by adversarial samples to make wrong predictions. To alleviate this negative effect, in this paper, we investigate the dependence between outputs of the target model and input adversarial samples from the perspective of information theory, and propose an adversarial defense method. |
DAWEI ZHOU et. al. | arxiv-cs.LG | 2022-07-25 |
| 243 | SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an effective and efficient segmentation attack method, dubbed SegPGD. |
Jindong Gu; Hengshuang Zhao; Volker Tresp; Philip Torr; | arxiv-cs.CV | 2022-07-25 |
| 244 | A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and Restoration Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Therefore, many recent works show emerging interest to take advantage of pre-trained GAN models by exploiting the well-disentangled latent space and the learned GAN priors. In this paper, we briefly review recent progress on leveraging pre-trained large-scale GAN models from three aspects, i.e., 1) the training of large-scale generative adversarial networks, 2) exploring and understanding the pre-trained GAN models, and 3) leveraging these models for subsequent tasks like image restoration and editing. |
Ming Liu; Yuxiang Wei; Xiaohe Wu; Wangmeng Zuo; Lei Zhang; | arxiv-cs.CV | 2022-07-21 |
| 245 | Decorrelative Network Architecture for Robust Electrocardiogram Classification Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel approach based on ensemble decorrelation and Fourier partitioning for training parallel network arms into a decorrelated architecture to learn complementary features, significantly reducing the chance of a perturbation fooling all arms of the deep learning model. |
Christopher Wiedeman; Ge Wang; | arxiv-cs.LG | 2022-07-18 |
| 246 | Adversarial Training Improves Joint Energy-Based Generative Modelling Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the novel framework for generative modelling using hybrid energy-based models. |
Rostislav Korst; Arip Asadulaev; | arxiv-cs.LG | 2022-07-18 |
| 247 | GANzilla: User-Driven Direction Discovery in Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Complementarily, we propose a GANzilla: a user-driven tool that empowers a user with the classic scatter/gather technique to iteratively discover directions to meet their editing goals. |
Noyan Evirgen; Xiang ‘Anthony’ Chen; | arxiv-cs.HC | 2022-07-17 |
| 248 | Threat Model-Agnostic Adversarial Defense Using Diffusion Models Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we follow the latter path and aim to develop a technique that leads to robust classifiers across various realizations of threat models. |
Tsachi Blau; Roy Ganz; Bahjat Kawar; Alex Bronstein; Michael Elad; | arxiv-cs.CV | 2022-07-17 |
| 249 | Structural Prior Guided Generative Adversarial Transformers for Low-Light Image Enhancement Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an effective Structural Prior guided Generative Adversarial Transformer (SPGAT) to solve low-light image enhancement. |
Cong Wang; Jinshan Pan; Xiao-Ming Wu; | arxiv-cs.CV | 2022-07-16 |
| 250 | A Neural Tangent Kernel Perspective of GANs Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We propose a novel theoretical framework of analysis for Generative Adversarial Networks (GANs). |
JEAN-YVES FRANCESCHI et. al. | icml | 2022-07-15 |
| 251 | Learning from Demonstration: Provably Efficient Adversarial Policy Imitation with Linear Function Approximation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study GAIL in both online and offline settings with linear function approximation, where both the transition and reward function are linear in the feature maps. |
Zhihan Liu; Yufeng Zhang; Zuyue Fu; Zhuoran Yang; Zhaoran Wang; | icml | 2022-07-15 |
| 252 | Learning Fair Representation with A Parametric Integral Probability Metric Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a new adversarial training scheme for LFR, where the integral probability metric (IPM) with a specific parametric family of discriminators is used. |
Dongha Kim; Kunwoong Kim; Insung Kong; Ilsang Ohn; Yongdai Kim; | icml | 2022-07-15 |
| 253 | Feasibility of Inconspicuous GAN-generated Adversarial Patches Against Object Detection Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Standard approaches for adversarial patch generation lead to noisy conspicuous patterns, which are easily recognizable by humans. Recent research has proposed several approaches to generate naturalistic patches using generative adversarial networks (GANs), yet only a few of them were evaluated on the object detection use case. |
Svetlana Pavlitskaya; Bianca-Marina Codău; J. Marius Zöllner; | arxiv-cs.CV | 2022-07-15 |
| 254 | ME-GAN: Learning Panoptic Electrocardio Representations for Multi-view ECG Synthesis Conditioned on Heart Diseases Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel disease-aware generative adversarial network for multi-view ECG synthesis called ME-GAN, which attains panoptic electrocardio representations conditioned on heart diseases and projects the representations onto multiple standard views to yield ECG signals. |
JINTAI CHEN et. al. | icml | 2022-07-15 |
| 255 | Generative Cooperative Networks for Natural Language Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce Generative Cooperative Networks, in which the discriminator architecture is cooperatively used along with the generation policy to output samples of realistic texts for the task at hand. |
SYLVAIN LAMPRIER et. al. | icml | 2022-07-15 |
| 256 | Principled Knowledge Extrapolation with GANs Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to study counterfactual synthesis from a new perspective of knowledge extrapolation, where a given knowledge dimension of the data distribution is extrapolated, but the remaining knowledge is kept indistinguishable from the original distribution. |
RUILI FENG et. al. | icml | 2022-07-15 |
| 257 | Conditional GANs with Auxiliary Discriminative Classifier Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: The fundamental reason pointed out in this paper is that the classifier of AC-GAN is generator-agnostic, which therefore cannot provide informative guidance for the generator to approach the joint distribution, resulting in a minimization of the conditional entropy that decreases the intra-class diversity. |
LIANG HOU et. al. | icml | 2022-07-15 |
| 258 | Generative Trees: Adversarial and Copycat Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a new path forward for the generation of tabular data, exploiting decades-old understanding of the supervised task’s best components for DT induction, from losses (properness), models (tree-based) to algorithms (boosting). |
Richard Nock; Mathieu Guillame-Bert; | icml | 2022-07-15 |
| 259 | Diffusion Models for Adversarial Purification Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we propose DiffPure that uses diffusion models for adversarial purification: Given an adversarial example, we first diffuse it with a small amount of noise following a forward diffusion process, and then recover the clean image through a reverse generative process. |
WEILI NIE et. al. | icml | 2022-07-15 |
| 260 | Bayesian Learning with Information Gain Provably Bounds Risk for A Robust Adversarial Defense Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a new algorithm to learn a deep neural network model robust against adversarial attacks. |
Bao Gia Doan; Ehsan M Abbasnejad; Javen Qinfeng Shi; Damith Ranashinghe; | icml | 2022-07-15 |
| 261 | A Branch and Bound Framework for Stronger Adversarial Attacks of ReLU Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we systematically search adversarial examples in the activation space of ReLU networks to tackle hard instances where none of the existing adversarial attacks succeed. |
HUAN ZHANG et. al. | icml | 2022-07-15 |
| 262 | Adversarial Vulnerability of Randomized Ensembles Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: However, this impressive performance raises the question: Are these robustness gains provided by randomized ensembles real? In this work we address this question both theoretically and empirically. |
Hassan Dbouk; Naresh Shanbhag; | icml | 2022-07-15 |
| 263 | Understanding Robust Overfitting of Adversarial Training and Beyond Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Given these observations, we further designed data ablation adversarial training and identify that some small-loss data which are not worthy of the adversary strength cause robust overfitting in the strong adversary mode. To relieve this issue, we propose minimum loss constrained adversarial training (MLCAT): in a minibatch, we learn large-loss data as usual, and adopt additional measures to increase the loss of the small-loss data. |
CHAOJIAN YU et. al. | icml | 2022-07-15 |
| 264 | On The Generalization Analysis of Adversarial Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the generalization properties of adversarial learning. |
Waleed Mustafa; Yunwen Lei; Marius Kloft; | icml | 2022-07-15 |
| 265 | RSD-GAN: Regularized Sobolev Defense GAN Against Speech-to-Text Adversarial Attacks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a new synthesis-based defense algorithm for counteracting with a varieties of adversarial attacks developed for challenging the performance of the cutting-edge speech-to-text transcription systems. |
Mohammad Esmaeilpour; Nourhene Chaalia; Patrick Cardinal; | arxiv-cs.SD | 2022-07-14 |
| 266 | Subband-based Generative Adversarial Network for Non-parallel Many-to-many Voice Conversion Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on one general setting, i.e., non-parallel many-to-many voice conversion, which is close to the real-world scenario. |
JIAN MA et. al. | arxiv-cs.SD | 2022-07-13 |
| 267 | PIAT: Physics Informed Adversarial Training for Solving Partial Differential Equations Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose the physics informed adversarial training (PIAT) of neural networks for solving nonlinear differential equations (NDE). |
Simin Shekarpaz; Mohammad Azizmalayeri; Mohammad Hossein Rohban; | arxiv-cs.LG | 2022-07-13 |
| 268 | On The Robustness of Bayesian Neural Networks to Adversarial Attacks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we analyse the geometry of adversarial attacks in the large-data, overparameterized limit for Bayesian Neural Networks (BNNs). |
LUCA BORTOLUSSI et. al. | arxiv-cs.LG | 2022-07-13 |
| 269 | Generative Adversarial Framework for Cold-Start Item Recommendation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To this end, we propose a general framework named Generative Adversarial Recommendation (GAR). |
HAO CHEN et. al. | sigir | 2022-07-12 |
| 270 | TabSynDex: A Universal Metric for Robust Evaluation of Synthetic Tabular Data Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we propose a new universal metric, TabSynDex, for robust evaluation of synthetic data. |
Vikram S Chundawat; Ayush K Tarun; Murari Mandal; Mukund Lahoti; Pratik Narang; | arxiv-cs.LG | 2022-07-12 |
| 271 | GANzzle: Reframing Jigsaw Puzzle Solving As A Retrieval Task Using A Generative Mental Image Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Exploiting advancements in Generative Adversarial methods, we learn how to reconstruct the image given a set of unordered pieces, allowing the model to learn a joint embedding space to match an encoding of each piece to the cropped layer of the generator. |
Davide Talon; Alessio Del Bue; Stuart James; | arxiv-cs.CV | 2022-07-12 |
| 272 | Exploring Adversarial Examples and Adversarial Robustness of Convolutional Neural Networks By Mutual Information Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: The mechanisms behind adversarial examples and adversarial training are worth exploring. Therefore, this work investigates similarities and differences between normally trained CNNs (NT-CNNs) and adversarially trained CNNs (AT-CNNs) in information extraction from the mutual information perspective. |
Jiebao Zhang; Wenhua Qian; Rencan Nie; Jinde Cao; Dan Xu; | arxiv-cs.LG | 2022-07-12 |
| 273 | Adversarial Robustness Assessment of NeuroEvolution Approaches Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we evaluate the adversarial robustness of models found by two prominent NeuroEvolution approaches on the CIFAR-10 image classification task: DENSER and NSGA-Net. |
Inês Valentim; Nuno Lourenço; Nuno Antunes; | arxiv-cs.NE | 2022-07-12 |
| 274 | A Generative Deep Learning Approach for Shape Recognition of Arbitrary Objects from Phaseless Acoustic Scattering Data Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose and demonstrate a generative deep learning approach for the shape recognition of an arbitrary object from its acoustic scattering properties. |
W. W. Ahmed; M. Farhat; P. -Y. Chen; X. Zhang; Y. Wu; | arxiv-cs.SD | 2022-07-12 |
| 275 | Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utility Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Then, we construct the deep variational CLUB (DVCLUB) models by employing neural networks to parameterize variational approximations of the associated information quantities. Building upon these information quantities, we present unified objectives of the supervised and unsupervised DVCLUB models. |
Behrooz Razeghi; Flavio P. Calmon; Deniz Gunduz; Slava Voloshynovskiy; | arxiv-cs.LG | 2022-07-11 |
| 276 | Statistical Detection of Adversarial Examples in Blockchain-based Federated Forest In-vehicle Network Intrusion Detection Systems Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We proposed integrating a statistical detector to detect and extract unknown adversarial samples. |
Ibrahim Aliyu; Selinde van Engelenburg; Muhammed Bashir Muazu; Jinsul Kim; Chang Gyoon Lim; | arxiv-cs.CR | 2022-07-11 |
| 277 | Models in The Loop: Aiding Crowdworkers with Generative Annotation Assistants Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we examine whether we can maintain the advantages of DADC, without incurring the additional cost. |
MAX BARTOLO et. al. | naacl | 2022-07-09 |
| 278 | Generative Adversarial Networks and Other Generative Models Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This chapter gives a basic introduction into the motivation for Generative Adversarial Networks (GANs) and traces the path of their success by abstracting the basic task and working mechanism, and deriving the difficulty of early practical approaches. |
Markus Wenzel; | arxiv-cs.CV | 2022-07-08 |
| 279 | Guiding The Retraining of Convolutional Neural Networks Against Adversarial Inputs Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our goal is to improve the models against adversarial inputs regarding accuracy, resource utilization and time from the point of view of a data scientist in the context of image classification. |
Francisco Durán López; Silverio Martínez-Fernández; Michael Felderer; Xavier Franch; | arxiv-cs.SE | 2022-07-08 |
| 280 | Jacobian Norm with Selective Input Gradient Regularization for Improved and Interpretable Adversarial Defense Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel approach based on Jacobian norm and Selective Input Gradient Regularization (J-SIGR), which suggests the linearized robustness through Jacobian normalization and also regularizes the perturbation-based saliency maps to imitate the model’s interpretable predictions. |
DEYIN LIU et. al. | arxiv-cs.LG | 2022-07-08 |
| 281 | On The Relationship Between Adversarial Robustness and Decision Region in Deep Neural Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we perform an empirical study to analyze the internal properties of DNNs that affect model robustness under adversarial attacks. |
Seongjin Park; Haedong Jeong; Giyoung Jeon; Jaesik Choi; | arxiv-cs.LG | 2022-07-07 |
| 282 | Text to Image Synthesis Using Stacked Conditional Variational Autoencoders and Conditional Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Taking into account the relative advantages of both GANs and VAEs, we proposed a new stacked Conditional VAE (CVAE) and Conditional GAN (CGAN) network architecture for synthesizing images conditioned on a text description. |
Haileleol Tibebu; Aadil Malik; Varuna De Silva; | arxiv-cs.CV | 2022-07-06 |
| 283 | Exploring Generative Adversarial Networks for Text-to-Image Generation with Evolution Strategies Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we follow a different direction by proposing the use of Covariance Matrix Adaptation Evolution Strategy to explore the latent space of Generative Adversarial Networks. |
Victor Costa; Nuno Lourenço; João Correia; Penousal Machado; | arxiv-cs.NE | 2022-07-06 |
| 284 | Cooperative Distribution Alignment Via JSD Upper Bound Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: A few recent works explore non-adversarial flow-based (i.e., invertible) approaches, but they lack a unified perspective and are limited in efficiently aligning multiple distributions. Therefore, we propose to unify and generalize previous flow-based approaches under a single non-adversarial framework, which we prove is equivalent to minimizing an upper bound on the Jensen-Shannon Divergence (JSD). |
Wonwoong Cho; Ziyu Gong; David I. Inouye; | arxiv-cs.LG | 2022-07-05 |
| 285 | TMGAN-PLC: Audio Packet Loss Concealment Using Temporal Memory Generative Adversarial Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a temporal memory generative adversarial network for audio PLC, dubbed TMGAN-PLC, which is comprised of a novel nested-UNet generator and the time-domain/frequency-domain discriminators. |
Yuansheng Guan; Guochen Yu; Andong Li; Chengshi Zheng; Jie Wang; | arxiv-cs.SD | 2022-07-04 |
| 286 | Stochastic Restoration of Heavily Compressed Musical Audio Using Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In such a scenario, there is no unique solution for the restoration of the original signal. Therefore, in this study, we test a stochastic generator of a Generative Adversarial Network (GAN) architecture for this task. |
Stefan Lattner; Javier Nistal; | arxiv-cs.SD | 2022-07-04 |
| 287 | Wild Networks: Exposure of 5G Network Infrastructures to Adversarial Examples Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Proactive assessment of such risks is also challenging due to the lack of ML-powered 5G equipment available for adversarial ML research. To tackle these problems, we propose a novel adversarial ML threat model that is particularly suited to 5G scenarios, and is agnostic to the precise function solved by ML. |
Giovanni Apruzzese; Rodion Vladimirov; Aliya Tastemirova; Pavel Laskov; | arxiv-cs.CR | 2022-07-04 |
| 288 | Hessian-Free Second-Order Adversarial Examples for Adversarial Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an approximation method through transforming the problem into an optimization in the Krylov subspace, which remarkably reduce the computational complexity to speed up the training procedure. |
YAGUAN QIAN et. al. | arxiv-cs.LG | 2022-07-04 |
| 289 | Cycle-Interactive Generative Adversarial Network for Robust Unsupervised Low-Light Enhancement Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Herein, we propose a novel Cycle-Interactive Generative Adversarial Network (CIGAN) for unsupervised low-light image enhancement, which is capable of not only better transferring illumination distributions between low/normal-light images but also manipulating detailed signals between two domains, e.g., suppressing/synthesizing realistic noise in the cyclic enhancement/degradation process. |
ZHANGKAI NI et. al. | arxiv-cs.CV | 2022-07-03 |
| 290 | Generating Gender-ambiguous Voices for Privacy-preserving Speech Recognition Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To prevent attribute inference attacks alongside speech recognition tasks, we present a generative adversarial network, GenGAN, that synthesises voices that conceal the gender or identity of a speaker. |
Dimitrios Stoidis; Andrea Cavallaro; | arxiv-cs.SD | 2022-07-03 |
| 291 | Anomaly Detection with Adversarially Learned Perturbations of Latent Space Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we have designed an adversarial framework consisting of two competing components, an Adversarial Distorter, and an Autoencoder. |
Vahid Reza Khazaie; Anthony Wong; John Taylor Jewell; Yalda Mohsenzadeh; | arxiv-cs.CV | 2022-07-03 |
| 292 | Backdoor Attack Is A Devil in Federated GAN-based Medical Image Synthesis Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this study, we propose a way of attacking federated GAN (FedGAN) by treating the discriminator with a commonly used data poisoning strategy in backdoor attack classification models. |
Ruinan Jin; Xiaoxiao Li; | arxiv-cs.CV | 2022-07-02 |
| 293 | BadHash: Invisible Backdoor Attacks Against Deep Hashing with Clean Label Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose BadHash, the first generative-based imperceptible backdoor attack against deep hashing, which can effectively generate invisible and input-specific poisoned images with clean label. |
SHENGSHAN HU et. al. | arxiv-cs.CV | 2022-07-01 |
| 294 | Effect of Homomorphic Encryption on The Performance of Training Federated Learning Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The classic centralized approach would involve sending the data to a centralized server where the model would be trained. |
Ignjat Pejic; Rui Wang; Kaitai Liang; | arxiv-cs.CR | 2022-07-01 |
| 295 | Art Creation with Multi-Conditional StyleGANs Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a multi-conditional Generative Adversarial Network (GAN) approach trained on large amounts of human paintings to synthesize realistic-looking paintings that emulate human art. |
KONSTANTIN DOBLER et. al. | ijcai | 2022-07-01 |
| 296 | Towards Creativity Characterization of Generative Models Via Group-Based Subset Scanning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thus, incorporating research on human creativity into generative deep learning techniques presents an opportunity to make their outputs more compelling and human-like. |
CELIA CINTAS et. al. | ijcai | 2022-07-01 |
| 297 | Logically Consistent Adversarial Attacks for Soft Theorem Provers Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Recent efforts within the AI community have yielded impressive results towards “soft theorem proving” over natural language sentences using language models. We propose a novel, generative adversarial framework for probing and improving these models’ reasoning capabilities. |
Alexander Gaskell; Yishu Miao; Francesca Toni; Lucia Specia; | ijcai | 2022-07-01 |
| 298 | Data-Free Adversarial Knowledge Distillation for Graph Neural Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, most of the existing KD methods require a large volume of real data, which are not readily available in practice, and may preclude their applicability in scenarios where the teacher model is trained on rare or hard to acquire datasets. To address this problem, we propose the first end-to-end framework for data-free adversarial knowledge distillation on graph structured data (DFAD-GNN). |
Yuanxin Zhuang; Lingjuan Lyu; Chuan Shi; Carl Yang; Lichao Sun; | ijcai | 2022-07-01 |
| 299 | Can We Find Neurons That Cause Unrealistic Images in Deep Generative Networks? Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this study, by analyzing the statistics and the roles for those neurons, we empirically show that rarely activated neurons are related to the failure results of making diverse objects and inducing artifacts. |
Hwanil Choi; Wonjoon Chang; Jaesik Choi; | ijcai | 2022-07-01 |
| 300 | Transformer-based Objective-reinforced Generative Adversarial Network to Generate Desired Molecules Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a transformer-based objective-reinforced generative adversarial network (TransORGAN) to generate molecules. |
Chen Li; Chikashige Yamanaka; Kazuma Kaitoh; Yoshihiro Yamanishi; | ijcai | 2022-07-01 |
| 301 | High-Resolution and Arbitrary-Sized Chinese Landscape Painting Creation Based on Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper outlines an automated creation system for Chinese landscape paintings based on generative adversarial networks. |
Peixiang Luo; Jinchao Zhang; Jie Zhou; | ijcai | 2022-07-01 |
| 302 | Style Fader Generative Adversarial Networks for Style Degree Controllable Artistic Style Transfer Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the issue, in this paper, we propose a novel method that for the first time allows adjusting the style degree for existing GAN-based artistic style transfer frameworks in real time after training. |
ZHIWEN ZUO et. al. | ijcai | 2022-07-01 |
| 303 | Robust Weight Perturbation for Adversarial Training Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: A criterion that regulates the weight perturbation is therefore crucial for adversarial training. In this paper, we propose such a criterion, namely Loss Stationary Condition (LSC) for constrained perturbation. |
CHAOJIAN YU et. al. | ijcai | 2022-07-01 |
| 304 | Efficient Adversarial Training With Data Pruning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we demonstrate data pruning-a method for increasing adversarial training efficiency through data sub-sampling. |
Maximilian Kaufmann; Yiren Zhao; Ilia Shumailov; Robert Mullins; Nicolas Papernot; | arxiv-cs.LG | 2022-07-01 |
| 305 | CAT: Customized Adversarial Training for Improved Robustness Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, we show it would lead worse training and generalizaiton error and forcing the prediction to match one-hot label. In this paper, therefore, we propose a new algorithm, named Customized Adversarial Training (CAT), which adaptively customizes the perturbation level and the corresponding label for each training sample in adversarial training. |
Minhao Cheng; Qi Lei; Pin-Yu Chen; Inderjit Dhillon; Cho-Jui Hsieh; | ijcai | 2022-07-01 |
| 306 | Learning Diverse and Physically Feasible Dexterous Grasps with Generative Model and Bilevel Optimization Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an integrative approach of combining a generative model and a bilevel optimization to compute diverse grasps for novel unseen objects. |
Albert Wu; Michelle Guo; C. Karen Liu; | arxiv-cs.RO | 2022-07-01 |
| 307 | Interpretable Melody Generation from Lyrics with Discrete-Valued Adversarial Training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In our proposal, we demonstrate our proposed interpretable lyrics-to-melody generation system which can interact with users to understand the generation process and recreate the desired songs. |
Wei Duan; Zhe Zhang; Yi Yu; Keizo Oyama; | arxiv-cs.SD | 2022-06-30 |
| 308 | Detecting and Recovering Adversarial Examples from Extracting Non-robust and Highly Predictive Adversarial Perturbations Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thus, based on high-dimension perturbation extraction, we propose a model-free AEs detection method, the whole process of which is free from querying the victim model. |
MINGYU DONG et. al. | arxiv-cs.CV | 2022-06-30 |
| 309 | Semantic Unfolding of StyleGAN Latent Space Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we identify that the facial attribute disentanglement is not optimal, thus facial editing relying on linear attribute separation is flawed. |
Mustafa Shukor; Xu Yao; Bharath Bushan Damodaran; Pierre Hellier; | arxiv-cs.CV | 2022-06-29 |
| 310 | SPI-GAN: Distilling Score-based Generative Models with Straight-Path Interpolations Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an enhanced distillation method, called straight-path interpolation GAN (SPI-GAN), which can be compared to the state-of-the-art shortcut-based distillation method, called denoising diffusion GAN (DD-GAN). |
Jinsung Jeon; Noseong Park; | arxiv-cs.LG | 2022-06-29 |
| 311 | DrumGAN VST: A Plugin for Drum Sound Analysis/Synthesis With Autoencoding Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present DrumGAN VST, a plugin for synthesizing drum sounds using a Generative Adversarial Network. |
Javier Nistal; Cyran Aouameur; Ithan Velarde; Stefan Lattner; | arxiv-cs.SD | 2022-06-29 |
| 312 | 3D-Aware Video Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: With our work, we explore 4D generative adversarial networks (GANs) that learn unconditional generation of 3D-aware videos. |
SHERWIN BAHMANI et. al. | arxiv-cs.CV | 2022-06-29 |
| 313 | GAN-based Intrinsic Exploration For Sample Efficient Reinforcement Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we address the problem of efficient exploration in reinforcement learning. |
Doğay Kamar; Nazım Kemal Üre; Gözde Ünal; | arxiv-cs.LG | 2022-06-28 |
| 314 | Generative Neural Articulated Radiance Fields Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: These 3D GANs, however, have not been demonstrated for human bodies and the generated radiance fields of existing frameworks are not directly editable, limiting their applicability in downstream tasks. We propose a solution to these challenges by developing a 3D GAN framework that learns to generate radiance fields of human bodies or faces in a canonical pose and warp them using an explicit deformation field into a desired body pose or facial expression. |
ALEXANDER W. BERGMAN et. al. | arxiv-cs.CV | 2022-06-28 |
| 315 | On The Rényi Cross-Entropy Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The R\'{e}nyi cross-entropy measure between two distributions, a generalization of the Shannon cross-entropy, was recently used as a loss function for the improved design of deep learning generative adversarial networks. In this work, we examine the properties of this measure and derive closed-form expressions for it when one of the distributions is fixed and when both distributions belong to the exponential family. |
Ferenc Cole Thierrin; Fady Alajaji; Tamás Linder; | arxiv-cs.IT | 2022-06-28 |
| 316 | A Deep Learning Approach to Create DNS Amplification Attacks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show in this work that both image processing and natural language processing adversarial learning algorithms can be applied against a network intrusion detection neural network. |
Jared Mathews; Prosenjit Chatterjee; Shankar Banik; Cory Nance; | arxiv-cs.CR | 2022-06-28 |
| 317 | Sound Model Factory: An Integrated System Architecture for Generative Audio Modelling Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a new system for data-driven audio sound model design built around two different neural network architectures, a Generative Adversarial Network(GAN) and a Recurrent Neural Network (RNN), that takes advantage of the unique characteristics of each to achieve the system objectives that neither is capable of addressing alone. |
Lonce Wyse; Purnima Kamath; Chitralekha Gupta; | arxiv-cs.SD | 2022-06-27 |
| 318 | Defense Against Adversarial Attacks on Deep Convolutional Neural Networks Through Nonlocal Denoising Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Despite substantial advances in network architecture performance, the susceptibility of adversarial attacks makes deep learning challenging to implement in safety-critical applications. This paper proposes a data-centric approach to addressing this problem. |
Sandhya Aneja; Nagender Aneja; Pg Emeroylariffion Abas; Abdul Ghani Naim; | arxiv-cs.CV | 2022-06-25 |
| 319 | Adversarial Robustness of Deep Neural Networks: A Survey from A Formal Verification Perspective Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we survey existing literature in adversarial robustness verification for neural networks and collect 39 diversified research works across machine learning, security, and software engineering domains. |
MARK HUASONG MENG et. al. | arxiv-cs.CR | 2022-06-24 |
| 320 | Learning Agile Skills Via Adversarial Imitation of Rough Partial Demonstrations Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a generative adversarial method for inferring reward functions from partial and potentially physically incompatible demonstrations for successful skill acquirement where reference or expert demonstrations are not easily accessible. |
CHENHAO LI et. al. | arxiv-cs.RO | 2022-06-23 |
| 321 | LED: Latent Variable-based Estimation of Density Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we propose LED, a new generative model closely related to GANs, that allows not only efficient sampling but also efficient density estimation. |
Omri Ben-Dov; Pravir Singh Gupta; Victoria Fernandez Abrevaya; Michael J. Black; Partha Ghosh; | arxiv-cs.LG | 2022-06-23 |
| 322 | A Study on The Evaluation of Generative Models Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study the evaluation metrics of generative models by generating a high-quality synthetic dataset on which we can estimate classical metrics for comparison. |
Eyal Betzalel; Coby Penso; Aviv Navon; Ethan Fetaya; | arxiv-cs.LG | 2022-06-22 |
| 323 | Latent Policies for Adversarial Imitation Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: A key insight of this work is that performing imitation learning in a suitable latent task space makes the training process stable, even in challenging high-dimensional problems. |
Tianyu Wang; Nikhil Karnwal; Nikolay Atanasov; | arxiv-cs.LG | 2022-06-22 |
| 324 | Using EBGAN for Anomaly Intrusion Detection Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we put forward an EBGAN-based intrusion detection method, IDS-EBGAN, that classifies network records as normal traffic or malicious traffic. |
YI CUI et. al. | arxiv-cs.CR | 2022-06-21 |
| 325 | Quantifying Uncertainty In Traffic State Estimation Using Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we will inform the GAN based predictions using stochastic traffic flow models and develop a GAN based PIDL framework for TSE, named “PhysGAN-TSE. |
Zhaobin Mo; Yongjie Fu; Xuan Di; | arxiv-cs.LG | 2022-06-19 |
| 326 | StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We study the taxonomy of GAN approaches and present a new open-source library named StudioGAN. |
Minguk Kang; Joonghyuk Shin; Jaesik Park; | arxiv-cs.CV | 2022-06-19 |
| 327 | TrafficFlowGAN: Physics-informed Flow Based Generative Adversarial Network for Uncertainty Quantification Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper proposes the TrafficFlowGAN, a physics-informed flow based generative adversarial network (GAN), for uncertainty quantification (UQ) of dynamical systems. |
Zhaobin Mo; Yongjie Fu; Daran Xu; Xuan Di; | arxiv-cs.LG | 2022-06-18 |
| 328 | On The Role of Generalization in Transferability of Adversarial Examples Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to demonstrate the role of the generalization properties of the substitute classifier used for generating adversarial examples in the transferability of the attack scheme to unobserved NN classifiers. |
Yilin Wang; Farzan Farnia; | arxiv-cs.LG | 2022-06-18 |
| 329 | Landscape Learning for Neural Network Inversion Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a method that learns a loss landscape where gradient descent is efficient, bringing massive improvement and acceleration to the inversion process. |
Ruoshi Liu; Chengzhi Mao; Purva Tendulkar; Hao Wang; Carl Vondrick; | arxiv-cs.CV | 2022-06-17 |
| 330 | Texture Generation Using Graph Generative Adversarial Network And Differentiable Rendering Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We thus present a new system called a graph generative adversarial network (GGAN) that can generate textures which can be directly integrated into a given 3D mesh models with tools like Blender and Unreal Engine and can be simulated from any perspective and lighting condition easily. |
Dharma KC; Clayton T. Morrison; Bradley Walls; | arxiv-cs.CV | 2022-06-17 |
| 331 | Comment on Transferability and Input Transformation with Additive Noise Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we analyze the relationship between transferability and input transformation with additive noise by mathematically proving that the modified optimization can produce more transferable adversarial examples. |
Hoki Kim; Jinseong Park; Jaewook Lee; | arxiv-cs.LG | 2022-06-17 |
| 332 | Analysis and Extensions of Adversarial Training for Video Classification Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Our second contribution is to show that using a smaller (sub-optimal) attack budget at training time leads to a more robust performance at test time. Based on these findings, we propose three defenses against attacks with variable attack budgets. |
Kaleab A. Kinfu; René Vidal; | arxiv-cs.CV | 2022-06-16 |
| 333 | Boosting The Adversarial Transferability of Surrogate Model with Dark Knowledge Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a method of training a surrogate model with abundant dark knowledge to boost the adversarial transferability of the adversarial examples generated by the surrogate model. |
Dingcheng Yang; Zihao Xiao; Wenjian Yu; | arxiv-cs.LG | 2022-06-16 |
| 334 | Adversarial Privacy Protection on Speech Enhancement Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we propose an adversarial method to degrade speech enhancement systems. |
Mingyu Dong; Diqun Yan; Rangding Wang; | arxiv-cs.SD | 2022-06-16 |
| 335 | Gradient-Based Adversarial and Out-of-Distribution Detection Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to utilize gradients for detecting adversarial and out-of-distribution samples. |
Jinsol Lee; Mohit Prabhushankar; Ghassan AlRegib; | arxiv-cs.LG | 2022-06-16 |
| 336 | Physics-Infused Fuzzy Generative Adversarial Network for Robust Failure Prognosis Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a novel hybrid modeling approach for prognostics applications based on combining concepts from fuzzy logic and generative adversarial networks (GANs) is outlined. |
Ryan Nguyen; Shubhendu Kumar Singh; Rahul Rai; | arxiv-cs.AI | 2022-06-15 |
| 337 | Hardening DNNs Against Transfer Attacks During Network Compression Using Greedy Adversarial Pruning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate the adversarial robustness of models produced by several irregular pruning schemes and by 8-bit quantization. |
Jonah O’Brien Weiss; Tiago Alves; Sandip Kundu; | arxiv-cs.LG | 2022-06-15 |
| 338 | Applications of Generative Adversarial Networks in Neuroimaging and Clinical Neuroscience Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We aim to bridge the gap between advanced deep learning methods and neurology research by highlighting how GANs can be leveraged to support clinical decision making and contribute to a better understanding of the structural and functional patterns of brain diseases. |
RONGGUANG WANG et. al. | arxiv-cs.LG | 2022-06-14 |
| 339 | Human Eyes Inspired Recurrent Neural Networks Are More Robust Against Adversarial Noises Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Inspired by the brain, we design recurrent neural networks, including an input sampler that mimics the human retina, a dorsal network that guides where to look next, and a ventral network that represents the retinal samples. Taking these modules together, the models learn to take multiple glances at an image, attend to a salient part at each glance, and accumulate the representation over time to recognize the image. |
Minkyu Choi; Yizhen Zhang; Kuan Han; Xiaokai Wang; Zhongming Liu; | arxiv-cs.CV | 2022-06-14 |
| 340 | Defending Observation Attacks in Deep Reinforcement Learning Via Detection and Denoising Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we consider attacks manifesting as perturbations in the observation space managed by the external environment. |
Zikang Xiong; Joe Eappen; He Zhu; Suresh Jagannathan; | arxiv-cs.LG | 2022-06-14 |
| 341 | Downlink Power Allocation in Massive MIMO Via Deep Learning: Adversarial Attacks and Training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The aim of this paper is twofold: (i) we consider a regression problem in a wireless setting and show that adversarial attacks can break the DL-based approach and (ii) we analyze the effectiveness of adversarial training as a defensive technique in adversarial settings and show that the robustness of DL-based wireless system against attacks improves significantly. |
B. R. Manoj; Meysam Sadeghi; Erik G. Larsson; | arxiv-cs.LG | 2022-06-14 |
| 342 | Exploring Adversarial Attacks and Defenses in Vision Transformers Trained with DINO Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This work conducts the first analysis on the robustness against adversarial attacks on self-supervised Vision Transformers trained using DINO. |
Javier Rando; Nasib Naimi; Thomas Baumann; Max Mathys; | arxiv-cs.CV | 2022-06-14 |
| 343 | Adversarial Vulnerability of Randomized Ensembles Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: However, this impressive performance raises the question: Are these robustness gains provided by randomized ensembles real? In this work we address this question both theoretically and empirically. |
Hassan Dbouk; Naresh R. Shanbhag; | arxiv-cs.LG | 2022-06-14 |
| 344 | When Adversarial Attacks Become Interpretable Counterfactual Explanations Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We argue that, when learning a 1-Lipschitz neural network with the dual loss of an optimal transportation problem, the gradient of the model is both the direction of the transportation plan and the direction to the closest adversarial attack. |
Mathieu Serrurier; Franck Mamalet; Thomas Fel; Louis Béthune; Thibaut Boissin; | arxiv-cs.AI | 2022-06-14 |
| 345 | Distributed Adversarial Training to Robustify Deep Neural Networks at Scale Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Spurred by that, we propose distributed adversarial training (DAT), a large-batch adversarial training framework implemented over multiple machines. |
GAOYUAN ZHANG et. al. | arxiv-cs.LG | 2022-06-13 |
| 346 | Security of Machine Learning-Based Anomaly Detection in Cyber Physical Systems Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we focus on the impact of adversarial attacks on deep learning-based anomaly detection in CPS networks and implement a mitigation approach against the attack by retraining models using adversarial samples. |
ZAHRA JADIDI et. al. | arxiv-cs.DC | 2022-06-12 |
| 347 | Early Transferability of Adversarial Examples in Deep Neural Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: What we discovered was that these two adversarial directions started to align with each other already after the first few training steps (which typically use only a small fraction of the available training data), even though the accuracy of the two networks hadn’t started to improve from their initial bad values due to the early stage of the training. The purpose of this paper is to present this phenomenon experimentally and propose plausible explanations for some of its properties. |
Oriel BenShmuel; | arxiv-cs.LG | 2022-06-09 |
| 348 | ReFace: Real-time Adversarial Attacks on Face Recognition Systems Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose ReFace, a real-time, highly-transferable attack on face recognition models based on Adversarial Transformation Networks (ATNs). |
SHEHZEEN HUSSAIN et. al. | arxiv-cs.CV | 2022-06-09 |
| 349 | Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Adversarial examples, which are usually generated for specific inputs with a specific model, are ubiquitous for neural networks. In this paper we unveil a surprising property of adversarial noises when they are put together, i.e., adversarial noises crafted by one-step gradient methods are linearly separable if equipped with the corresponding labels. |
Huishuai Zhang; Da Yu; Yiping Lu; Di He; | arxiv-cs.LG | 2022-06-09 |
| 350 | CARLA-GeAR: A Dataset Generator for A Systematic Evaluation of Adversarial Robustness of Vision Models Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: All the code and datasets used in this paper are available at http://carlagear.retis.santannapisa.it. |
Federico Nesti; Giulio Rossolini; Gianluca D’Amico; Alessandro Biondi; Giorgio Buttazzo; | arxiv-cs.CV | 2022-06-09 |
| 351 | GAN I Hire You? — A System for Personalized Virtual Job Interview Training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: A technological approach for generating such feedback might be a playful and low-key starting point for job interview training. Therefore, we extended an interactive virtual job interview training system with a Generative Adversarial Network (GAN)-based approach that first detects behavioral weaknesses and subsequently generates personalized feedback. |
ALEXANDER HEIMERL et. al. | arxiv-cs.HC | 2022-06-08 |
| 352 | Wavelet Regularization Benefits Adversarial Training Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We propose a wavelet regularization method based on the Haar wavelet decomposition which is named Wavelet Average Pooling. |
JUN YAN et. al. | arxiv-cs.CV | 2022-06-08 |
| 353 | LADDER: Latent Boundary-guided Adversarial Training Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To achieve a better trade-off between standard accuracy and adversarial robustness, we propose a novel adversarial training framework called LAtent bounDary-guided aDvErsarial tRaining (LADDER) that adversarially trains DNN models on latent boundary-guided adversarial examples. |
Xiaowei Zhou; Ivor W. Tsang; Jie Yin; | arxiv-cs.LG | 2022-06-08 |
| 354 | Auditing Privacy Defenses in Federated Learning Via Generative Gradient Leakage Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we validate that the private training data can still be leaked under certain defense settings with a new type of leakage, i.e., Generative Gradient Leakage (GGL). |
Zhuohang Li; Jiaxin Zhang; Luyang Liu; Jian Liu; | cvpr | 2022-06-07 |
| 355 | DO-GAN: A Double Oracle Framework for Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new approach to train Generative Adversarial Networks (GANs) where we deploy a double-oracle framework using the generator and discriminator oracles. |
AYE PHYU PHYU AUNG et. al. | cvpr | 2022-06-07 |
| 356 | Feature Statistics Mixing Regularization for Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: As a remedy, we propose feature statistics mixing regularization (FSMR) that encourages the discriminator’s prediction to be invariant to the styles of input images. |
Junho Kim; Yunjey Choi; Youngjung Uh; | cvpr | 2022-06-07 |
| 357 | Protecting Facial Privacy: Generating Adversarial Identity Masks Via Style-Robust Makeup Transfer Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose adversarial makeup transfer GAN (AMT-GAN), a novel face protection method aiming at constructing adversarial face images that preserve stronger black-box transferability and better visual quality simultaneously. |
SHENGSHAN HU et. al. | cvpr | 2022-06-07 |
| 358 | Cycle-Consistent Counterfactuals By Latent Transformations Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel approach, Cycle-Consistent Counterfactuals by Latent Transformations (C3LT), which learns a latent transformation that automatically generates visual CFs by steering in the latent space of generative models. |
Saeed Khorram; Li Fuxin; | cvpr | 2022-06-07 |
| 359 | Learning To Restore 3D Face From In-the-Wild Degraded Images Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In-the-wild 3D face modelling is a challenging problem as the predicted facial geometry and texture suffer from a lack of reliable clues or priors, when the input images are degraded. To address such a problem, in this paper we propose a novel Learning to Restore (L2R) 3D face framework for unsupervised high-quality face reconstruction from low-resolution images. |
ZHENYU ZHANG et. al. | cvpr | 2022-06-07 |
| 360 | GCFSR: A Generative and Controllable Face Super Resolution Method Without Facial and GAN Priors Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we propose a generative and controllable face SR framework, called GCFSR, which can reconstruct images with faithful identity information without any additional priors. |
Jingwen He; Wu Shi; Kai Chen; Lean Fu; Chao Dong; | cvpr | 2022-06-07 |
| 361 | Depth-Aware Generative Adversarial Network for Talking Head Video Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we introduce a self-supervised face-depth learning method to automatically recover dense 3D facial geometry (i.e. depth) from the face videos without the requirement of any expensive 3D annotation data. |
Fa-Ting Hong; Longhao Zhang; Li Shen; Dan Xu; | cvpr | 2022-06-07 |
| 362 | SphericGAN: Semi-Supervised Hyper-Spherical Generative Adversarial Networks for Fine-Grained Image Synthesis Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To reduce the dependence of generative models on labeled data, we propose a semi-supervised hyper-spherical GAN for class-conditional fine-grained image generation, and our model is referred to as SphericGAN. |
TIANYI CHEN et. al. | cvpr | 2022-06-07 |
| 363 | Towards Efficient Data Free Black-Box Adversarial Attack Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, by rethinking the collaborative relationship between the generator and the substitute model, we design a novel black-box attack framework. |
JIE ZHANG et. al. | cvpr | 2022-06-07 |
| 364 | Few Shot Generative Model Adaption Via Relaxed Spatial Structural Alignment Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: However, existing methods are prone to model overfitting and collapse in extremely few shot setting (less than 10). To solve this problem, we propose a relaxed spatial structural alignment (RSSA) method to calibrate the target generative models during the adaption. |
Jiayu Xiao; Liang Li; Chaofei Wang; Zheng-Jun Zha; Qingming Huang; | cvpr | 2022-06-07 |
| 365 | Multi-View Consistent Generative Adversarial Networks for 3D-Aware Image Synthesis Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: However, one key challenge remains: existing approaches lack geometry constraints, hence usually fail to generate multi-view consistent images. To address this challenge, we propose Multi-View Consistent Generative Adversarial Networks (MVCGAN) for high-quality 3D-aware image synthesis with geometry constraints. |
XUANMENG ZHANG et. al. | cvpr | 2022-06-07 |
| 366 | Exemplar-Based Pattern Synthesis With Implicit Periodic Field Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an exemplar-based visual pattern synthesis framework that aims to model the inner statistics of visual patterns and generate new, versatile patterns that meet the aforementioned requirements. |
Haiwei Chen; Jiayi Liu; Weikai Chen; Shichen Liu; Yajie Zhao; | cvpr | 2022-06-07 |
| 367 | DetectorDetective: Investigating The Effects of Adversarial Examples on Object Detectors Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We propose DetectorDetective, an interactive visual tool that aims to help users better understand the behaviors of a model as adversarial images journey through an object detector. |
SIVAPRIYA VELLAICHAMY et. al. | cvpr | 2022-06-07 |
| 368 | LAS-AT: Adversarial Training With Learnable Attack Strategy Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a novel framework for adversarial training by introducing the concept of "learnable attack strategy", dubbed LAS-AT, which learns to automatically produce attack strategies to improve the model robustness. |
XIAOJUN JIA et. al. | cvpr | 2022-06-07 |
| 369 | Improving Adversarially Robust Few-Shot Image Classification With Generalizable Representations Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider the FSIC problem in the case of adversarial examples. |
Junhao Dong; Yuan Wang; Jian-Huang Lai; Xiaohua Xie; | cvpr | 2022-06-07 |
| 370 | Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To bridge adversarial robustness and model compression, we propose a novel adversarial pruning method, Masking Adversarial Damage (MAD) that employs second-order information of adversarial loss. |
Byung-Kwan Lee; Junho Kim; Yong Man Ro; | cvpr | 2022-06-07 |
| 371 | Understanding and Increasing Efficiency of Frank-Wolfe Adversarial Training Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We develop a theoretical framework for adversarial training with FW optimization (FW-AT) that reveals a geometric connection between the loss landscape and the distortion of l-inf FW attacks (the attack’s l-2 norm). |
Theodoros Tsiligkaridis; Jay Roberts; | cvpr | 2022-06-07 |
| 372 | Scene Aware Person Image Generation Through Global Contextual Conditioning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel pipeline to generate and insert contextually relevant person images into an existing scene while preserving the global semantics. |
Prasun Roy; Subhankar Ghosh; Saumik Bhattacharya; Umapada Pal; Michael Blumenstein; | arxiv-cs.CV | 2022-06-06 |
| 373 | Winner Does Not Take All: Contrasting Centrality in Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a random graph model that generates directed graphs with low-key leaders. |
Anthony Bonato; Joey Kapusin; Jiajie Yuan; | arxiv-cs.SI | 2022-06-05 |
| 374 | Soft Adversarial Training Can Retain Natural Accuracy Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a training framework that can retain natural accuracy without sacrificing robustness in a constrained setting. |
Abhijith Sharma; Apurva Narayan; | arxiv-cs.LG | 2022-06-04 |
| 375 | D’ARTAGNAN: Counterfactual Video Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We combine deep neural networks, twin causal networks and generative adversarial methods for the first time to build D’ARTAGNAN (Deep ARtificial Twin-Architecture GeNerAtive Networks), a novel causal generative model. |
HADRIEN REYNAUD et. al. | arxiv-cs.CV | 2022-06-03 |
| 376 | Causality Learning With Wasserstein Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: It simultaneously learns causal structures while improving its data generation capability. We compare the performance of DAG-WGAN with other models that do not involve the Wasserstein metric in order to identify its contribution to causal structure learning. |
Hristo Petkov; Colin Hanley; Feng Dong; | arxiv-cs.LG | 2022-06-03 |
| 377 | An Unpooling Layer for Graph Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel and trainable graph unpooling layer for effective graph generation. |
Yinglong Guo; Dongmian Zou; Gilad Lerman; | arxiv-cs.LG | 2022-06-03 |
| 378 | Model-Informed Generative Adversarial Network (MI-GAN) for Learning Optimal Power Flow Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an optimization model-informed generative adversarial network (MI-GAN) framework to solve OPF under uncertainty. |
Yuxuan Li; Chaoyue Zhao; Chenang Liu; | arxiv-cs.LG | 2022-06-03 |
| 379 | Adversarial Laser Spot: Robust and Covert Physical Adversarial Attack to DNNs Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The light-based physical adversarial attack technology has excellent covertness, which brings great security risks to many applications based on deep neural networks (such as automatic driving technology). Therefore, we propose a robust physical adversarial attack technology with excellent covertness, called adversarial laser point (AdvLS), which optimizes the physical parameters of laser point through genetic algorithm to perform physical adversarial attack. |
Chengyin Hu; | arxiv-cs.CV | 2022-06-02 |
| 380 | FACM: Correct The Output of Deep Neural Network with Middle Layers Features Against Adversarial Samples Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the strong adversarial attacks against deep neural network (DNN), the output of DNN will be misclassified if and only if the last feature layer of the DNN is completely destroyed by adversarial samples, while our studies found that the middle feature layers of the DNN can still extract the effective features of the original normal category in these adversarial attacks. To this end, in this paper, a middle $\bold{F}$eature layer $\bold{A}$nalysis and $\bold{C}$onditional $\bold{M}$atching prediction distribution (FACM) model is proposed to increase the robustness of the DNN against adversarial samples through correcting the output of DNN with the features extracted by the middle layers of DNN. |
Xiangyuan Yang; Jie Lin; Hanlin Zhang; Xinyu Yang; Peng Zhao; | arxiv-cs.CV | 2022-06-02 |
| 381 | The Robust Way to Stack and Bag: The Local Lipschitz Way Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Recent research has established that the local Lipschitz constant of a neural network directly influences its adversarial robustness. |
Thulasi Tholeti; Sheetal Kalyani; | arxiv-cs.LG | 2022-06-01 |
| 382 | On The Reversibility of Adversarial Attacks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the predictability of the mapping between the classes predicted for original images and for their corresponding adversarial examples. |
Chau Yi Li; Ricardo Sánchez-Matilla; Ali Shahin Shamsabadi; Riccardo Mazzon; Andrea Cavallaro; | arxiv-cs.LG | 2022-06-01 |
| 383 | Generative Models with Information-Theoretic Protection Against Membership Inference Attacks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an information theoretically motivated regularization term that prevents the generative model from overfitting to training data and encourages generalizability. |
Parisa Hassanzadeh; Robert E. Tillman; | arxiv-cs.LG | 2022-05-31 |
| 384 | Searching for The Essence of Adversarial Perturbations Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we demonstrate that adversarial perturbations contain human-recognizable information, which is the key conspirator responsible for a neural network’s erroneous prediction, in contrast to a widely discussed argument that human-imperceptible information plays the critical role in fooling a network. |
Dennis Y. Menn; Hung-yi Lee; | arxiv-cs.LG | 2022-05-30 |
| 385 | Why Adversarial Training of ReLU Networks Is Difficult? Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper mathematically derives an analytic solution of the adversarial perturbation on a ReLU network, and theoretically explains the difficulty of adversarial training. |
XU CHENG et. al. | arxiv-cs.LG | 2022-05-30 |
| 386 | Exposing Fine-grained Adversarial Vulnerability of Face Anti-spoofing Models Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: So we propose fine-grained attacks for exposing adversarial vulnerability of face anti-spoofing models. |
Songlin Yang; Wei Wang; Chenye Xu; Bo Peng; Jing Dong; | arxiv-cs.CV | 2022-05-30 |
| 387 | Robust Weight Perturbation for Adversarial Training Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: A criterion that regulates the weight perturbation is therefore crucial for adversarial training. In this paper, we propose such a criterion, namely Loss Stationary Condition (LSC) for constrained perturbation. |
CHAOJIAN YU et. al. | arxiv-cs.LG | 2022-05-29 |
| 388 | Enhancing Quality of Pose-varied Face Restoration with Local Weak Feature Sensing and GAN Prior Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a well-designed blind face restoration network with generative facial prior. |
KAI HU et. al. | arxiv-cs.CV | 2022-05-28 |
| 389 | Multiscale Voxel Based Decoding For Enhanced Natural Image Reconstruction From Brain Activity Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we present a novel approach for enhanced image reconstruction, in which existing methods for object decoding and image reconstruction are merged together. |
Mali Halac; Murat Isik; Hasan Ayaz; Anup Das; | arxiv-cs.CV | 2022-05-27 |
| 390 | Misleading Deep-Fake Detection with GAN Fingerprints Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: These attacks, however, still require certain conditions to hold, such as interacting with the detection method or adjusting the GAN directly. In this paper, we introduce a novel class of simple counterattacks that overcomes these limitations. |
Vera Wesselkamp; Konrad Rieck; Daniel Arp; Erwin Quiring; | arxiv-cs.CV | 2022-05-25 |
| 391 | DH-GAN: A Physics-driven Untrained Generative Adversarial Network for 3D Microscopic Imaging Using Digital Holography Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a new DL architecture based on generative adversarial networks that uses a discriminative network for realizing a semantic measure for reconstruction quality while using a generative network as a function approximator to model the inverse of hologram formation. |
Xiwen Chen; Hao Wang; Abolfazl Razi; Michael Kozicki; Christopher Mann; | arxiv-cs.IR | 2022-05-25 |
| 392 | Learning Distributions By Generative Adversarial Networks: Approximation and Generalization Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study how well generative adversarial networks (GAN) learn probability distributions from finite samples by analyzing the convergence rates of these models. |
Yunfei Yang; | arxiv-cs.LG | 2022-05-25 |
| 393 | Highly Accurate FMRI ADHD Classification Using Time Distributed Multi Modal 3D CNNs Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This work proposes an algorithm for fMRI data analysis for the classification of ADHD disorders. |
Christopher Sims; | arxiv-cs.LG | 2022-05-24 |
| 394 | Diffuse Map Guiding Unsupervised Generative Adversarial Network for SVBRDF Estimation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we use the Cook-Torrance model to reconstruct the materials. |
Zhiyao Luo; Hongnan Chen; | arxiv-cs.CV | 2022-05-24 |
| 395 | Time-series Transformer Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Many downstream tasks learn to model conditional distributions of the time-series, hence, synthetic data drawn from a generative model must satisfy 1) in addition to performing 2). We present TsT-GAN, a framework that capitalises on the Transformer architecture to satisfy the desiderata and compare its performance against five state-of-the-art models on five datasets and show that TsT-GAN achieves higher predictive performance on all datasets. |
Padmanaba Srinivasan; William J. Knottenbelt; | arxiv-cs.LG | 2022-05-23 |
| 396 | RCC-GAN: Regularized Compound Conditional GAN for Large-Scale Tabular Data Synthesis Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a novel generative adversarial network (GAN) for synthesizing large-scale tabular databases which contain various features such as continuous, discrete, and binary. |
MOHAMMAD ESMAEILPOUR et. al. | arxiv-cs.LG | 2022-05-23 |
| 397 | Falsification of Multiple Requirements for Cyber-Physical Systems Using Online Generative Adversarial Networks and Multi-Armed Bandits Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, our focus is in falsifying systems with multiple requirements. |
Jarkko Peltomäki; Ivan Porres; | arxiv-cs.LG | 2022-05-23 |
| 398 | Wasserstein Generative Adversarial Networks for Online Test Generation for Cyber Physical Systems Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel online test generation algorithm WOGAN based on Wasserstein Generative Adversarial Networks. |
Jarkko Peltomäki; Frankie Spencer; Ivan Porres; | arxiv-cs.LG | 2022-05-23 |
| 399 | WOGAN at The SBST 2022 CPS Tool Competition Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: WOGAN is an online test generation algorithm based on Wasserstein generative adversarial networks. In this note, we present how WOGAN works and summarize its performance in the SBST 2022 CPS tool competition concerning the AI of a self-driving car. |
Jarkko Peltomäki; Frankie Spencer; Ivan Porres; | arxiv-cs.RO | 2022-05-23 |
| 400 | Collaborative Adversarial Training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we highlight that some collaborative examples, nearly perceptually indistinguishable from both adversarial and benign examples yet show extremely lower prediction loss, can be utilized to enhance adversarial training. |
Qizhang Li; Yiwen Guo; Wangmeng Zuo; Hao Chen; | arxiv-cs.LG | 2022-05-23 |
| 401 | Diverse Audio Captioning Via Adversarial Training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: As different people may describe an audio clip from different aspects using distinct words and grammars, we argue that an audio captioning system should have the ability to generate diverse captions for a fixed audio clip and across similar audio clips. To address this problem, we propose an adversarial training framework for audio captioning based on a conditional generative adversarial network (C-GAN), which aims at improving the naturalness and diversity of generated captions. |
X. Mei; X. Liu; J. Sun; M. D. Plumbley; W. Wang; | icassp | 2022-05-22 |
| 402 | Superresolution and Segmentation of OCT Scans Using Multi-Stage Adversarial Guided Attention Training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work aims to segment the OCT images automatically; however, it is a challenging task due to various issues such as the speckle noise, small target region, and unfavorable imaging conditions. |
P. JEIHOUNI et. al. | icassp | 2022-05-22 |
| 403 | Speech Enhancement for Low Bit Rate Speech Codec Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a neural extension to low bit rate speech codec (e.g., Codec2) that aims to improve the perceptual quality of synthesized speech. |
J. Lin; K. Kalgaonkar; Q. He; X. Lei; | icassp | 2022-05-22 |
| 404 | Generative Adversarial Network Including Referring Image Segmentation For Text-Guided Image Manipulation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a novel generative adversarial network to improve the performance of image manipulation using natural language descriptions that contain desired attributes. |
Y. Watanabe; R. Togo; K. Maeda; T. Ogawa; M. Haseyama; | icassp | 2022-05-22 |
| 405 | Eyes Tell All: Irregular Pupil Shapes Reveal GAN-Generated Faces Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that GAN-generated faces can be exposed via irregular pupil shapes. |
H. Guo; S. Hu; X. Wang; M. -C. Chang; S. Lyu; | icassp | 2022-05-22 |
| 406 | Simpler Is Better: Spectral Regularization and Up-Sampling Techniques for Variational Autoencoders Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a 2D Fourier transform-based spectral regularization loss and evaluate it on the variational autoencoder. |
S. Bj�rk; J. N. Myhre; T. Haugland Johansen; | icassp | 2022-05-22 |
| 407 | Composing Graphical Models with Generative Adversarial Networks for EEG Signal Modeling Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose a generative and inference approach that combines the complementary benefits of probabilistic graphical models and generative adversarial networks (GANs) for EEG signal modeling. |
K. Vo; M. Vishwanath; R. Srinivasan; N. Dutt; H. Cao; | icassp | 2022-05-22 |
| 408 | VSEGAN: Visual Speech Enhancement Generative Adversarial Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a novel framework that involves visual information for speech enhancement, by incorporating a Generative Adversarial Network (GAN). |
X. Xu; et al. | icassp | 2022-05-22 |
| 409 | Automatic DJ Transitions with Differentiable Audio Effects and Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore a data-driven approach that uses a generative adversarial network to create the song transition by learning from real-world DJ mixes. |
B. -Y. CHEN et. al. | icassp | 2022-05-22 |
| 410 | Optimizing Latent Space Directions for Gan-Based Local Image Editing Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We thus present a novel objective function to evaluate the locality of an image edit. |
E. Pajouheshgar; T. Zhang; S. S�sstrunk; | icassp | 2022-05-22 |
| 411 | Bi-Directional Normalization and Color Attention-Guided Generative Adversarial Network for Image Enhancement Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a bi-directional normalization and color attention-guided generative adversarial network (BNCAGAN) for unsupervised image enhancement. |
S. Liu; G. Xiao; X. Xu; S. Wu; | icassp | 2022-05-22 |
| 412 | PU-Refiner: A Geometry Refiner with Adversarial Learning for Point Cloud Upsampling Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present PU-Refiner, a generative adversarial network for point cloud upsampling. |
H. Liu; H. Yuan; R. Hamzaoui; W. Gao; S. Li; | icassp | 2022-05-22 |
| 413 | Adversarial Audio Synthesis Using A Harmonic-Percussive Discriminator Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a discriminator design scheme for generative adversarial network-based audio signal generation. |
J. Lee; H. Lim; C. Lee; I. Jang; H. -G. Kang; | icassp | 2022-05-22 |
| 414 | Sparsity Improves Unsupervised Attribute Discovery in Stylegan Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we identify a new criterion, representation sparsity, that allows us to produce extremely efficient yet diverse semantic directions in GAN (generative adversarial network) latent spaces. |
S. Liu; R. Anirudh; J. J. Thiagarajan; P. -T. Bremer; | icassp | 2022-05-22 |
| 415 | Noise-Robust Speech Recognition With 10 Minutes Unparalleled In-Domain Data Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a generative adversarial network to simulate noisy spectrum from the clean spectrum (SimuGAN), where only 10 minutes of unparalleled in-domain noisy speech data is required as labels. |
C. Chen; N. Hou; Y. Hu; S. Shirol; E. S. Chng; | icassp | 2022-05-22 |
| 416 | MBA-RainGAN: A Multi-Branch Attention Generative Adversarial Network for Mixture of Rain Removal Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we originally consider that the overall object visibility is determined by MOR, and enrich the RainCityscapes by considering real-world raindrops to construct the MOR dataset, named RainCityscapes++. |
Y. Shen; et al. | icassp | 2022-05-22 |
| 417 | DCNGAN: A Deformable Convolution-Based GAN with QP Adaptation for Perceptual Quality Enhancement of Compressed Video Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a deformable convolution-based generative adversarial network (DCNGAN) for perceptual quality enhancement of compressed videos. |
S. ZHANG et. al. | icassp | 2022-05-22 |
| 418 | Generation for Unsupervised Domain Adaptation: A Gan-Based Approach for Object Classification with 3D Point Cloud Data Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead of aligning features between source data and target data, we propose a method that uses a Generative Adversarial Network (GAN) to generate synthetic data from the source domain so that the output is close to the target domain. |
J. Huang; J. Yuan; C. Qiao; | icassp | 2022-05-22 |
| 419 | Real-World Adversarial Examples Via Makeup Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Herein, we propose a physical adversarial attack with the use of full-face makeup. |
C. -S. Lin; C. -Y. Hsu; P. -Y. Chen; C. -M. Yu; | icassp | 2022-05-22 |
| 420 | Improving Anomaly Detection with A Self-Supervised Task Based on Generative Adversarial Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We assume that the main reason is that these methods ignore the diversity of patterns in normal samples. To alleviate the above issue, this paper proposes a novel anomaly detection framework based on generative adversarial network, called ADe-GAN. |
H. CHAI et. al. | icassp | 2022-05-22 |
| 421 | DAM-GAN : Image Inpainting Using Dynamic Attention Map Based on Fake Texture Detection Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To reduce pixel inconsistency disorder resulted from fake textures, we introduce a GANbased model using dynamic attention map (DAM-GAN). |
D. Cha; D. Kim; | icassp | 2022-05-22 |
| 422 | Adversarial Learning in Transformer Based Neural Network in Radio Signal Classification Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, motivated by attractive classification performance of the transformer based neural networks, we analyse the vulnerability and robustness of the transformer against adversarial attacks in modulation classification scenarios. |
L. Zhang; S. Lambotharan; G. Zheng; | icassp | 2022-05-22 |
| 423 | Synthesis of Adversarial Samples in Two-Stage Classifiers Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the robustness of two Two-Stage Hierarchical Classifier models, the flat and top-down hierarchical classifiers, termed FHC and TDHC respectively, to targeted and confidence reduction attacks. |
I. R. Alkhouri; A. Velasquez; G. K. Atia; | icassp | 2022-05-22 |
| 424 | Adversarial Examples Detection Based on Error Level Analysis and Space Mapping Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Meanwhile, researchers have found that the stability of adversarial example after space mapping is worse than that of the clean example. Therefore, we propose a two-branch architecture to detect adversarial examples based on the aforementioned strategies. |
S. Huang; S. Wang; J. Chen; G. Li; W. Wang; | icassp | 2022-05-22 |
| 425 | Patch Steganalysis: A Sampling Based Defense Against Adversarial Steganography Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel sampling based defense method for steganalysis. |
C. Qin; N. Zhao; W. Zhang; N. Yu; | icassp | 2022-05-22 |
| 426 | Block-Sparse Adversarial Attack to Fool Transformer-Based Text Classifiers Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Recently, it has been shown that, in spite of the significant performance of deep neural networks in different fields, those are vulnerable to adversarial examples. In this pa-per, we propose a gradient-based adversarial attack against transformer-based text classifiers. |
S. Sadrizadeh; L. Dolamic; P. Frossard; | icassp | 2022-05-22 |
| 427 | Natural-Looking Adversarial Examples from Freehand Sketches Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we present a novel freehand sketch-based natural-looking adversarial example generator that we call SketchAdv. |
H. G. Kim; D. Nanni; S. S�sstrunk; | icassp | 2022-05-22 |
| 428 | Position-Invariant Adversarial Attacks on Neural Modulation Recognition Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the physical signal communication scenario, the adversarial signal transmitted by the adversary is affected by the channel, resulting in a random time delay with the original signal and causing decay on the attack performance. To ad-dress this issue, we propose the Position-Invariant adversarial attack Method (PIM) that generates the position-invariant adversarial signal by averaging the adversarial signals generated by shifted input signals to mitigate the channel effect on time delay. |
Z. YU et. al. | icassp | 2022-05-22 |
| 429 | Mitigating Closed-Model Adversarial Examples with Bayesian Neural Modeling for Enhanced End-to-End Speech Recognition Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim to enhance the system robustness of end-to-end automatic speech recognition (ASR) against adversarially-noisy speech examples. |
C. -H. H. Yang; et al. | icassp | 2022-05-22 |
| 430 | Adversary Distillation for One-Shot Attacks on 3D Target Tracking Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present an efficient generation based adversarial attack, termed Adversary Distillation Network (AD-Net), which is able to distract a victim tracker in a single shot. |
Z. WANG et. al. | icassp | 2022-05-22 |
| 431 | Effective and Inconspicuous Over-the-Air Adversarial Examples with Adaptive Filtering Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we demonstrate a novel audio-domain adversarial attack that modifies benign audio using an interpretable and differentiable parametric transformation – adaptive filtering. |
P. O�Reilly; P. Awasthi; A. Vijayaraghavan; B. Pardo; | icassp | 2022-05-22 |
| 432 | Cycle-GAN for Eye-tracking Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This manuscript presents a not typical implementation of the cycle generative adversarial networks (Cycle-GAN) method for eye-tracking tasks. |
Ildar Rakhmatulin; | arxiv-cs.CV | 2022-05-21 |
| 433 | Exploring The Trade-off Between Plausibility, Change Intensity and Adversarial Power in Counterfactual Explanations Using Multi-objective Optimization Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work we argue that automated counterfactual generation should regard several aspects of the produced adversarial instances, not only their adversarial capability. To this end, we present a novel framework for the generation of counterfactual examples which formulates its goal as a multi-objective optimization problem balancing three different objectives: 1) plausibility, i.e., the likeliness of the counterfactual of being possible as per the distribution of the input data; 2) intensity of the changes to the original input; and 3) adversarial power, namely, the variability of the model’s output induced by the counterfactual. |
Javier Del Ser; Alejandro Barredo-Arrieta; Natalia Díaz-Rodríguez; Francisco Herrera; Andreas Holzinger; | arxiv-cs.LG | 2022-05-20 |
| 434 | Defending Against Adversarial Attacks By Energy Storage Facility Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this research, we manifest that the adversarial algorithm attack induces a significant cost-increase risk which will be exacerbated by the growing penetration of intermittent renewable energy. |
Jiawei Li; Jianxiao Wang; Lin Chen; Yang Yu; | arxiv-cs.CR | 2022-05-19 |
| 435 | Revisiting PINNs: Generative Adversarial Physics-informed Neural Networks and Point-weighting Method Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose the generative adversarial physics-informed neural network (GA-PINN), which integrates the generative adversarial (GA) mechanism with the structure of PINNs, to improve the performance of PINNs by exploiting only a small size of exact solutions to the PDEs. |
Wensheng Li; Chao Zhang; Chuncheng Wang; Hanting Guan; Dacheng Tao; | arxiv-cs.LG | 2022-05-18 |
| 436 | Passive Defense Against 3D Adversarial Point Clouds Through The Lens of 3D Steganalysis Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: These point manipulations would modify geometrical properties and local correlations of benign point clouds more or less. Motivated by this basic fact, we propose to defend such adversarial examples with the aid of 3D steganalysis techniques. |
Jiahao Zhu; | arxiv-cs.MM | 2022-05-18 |
| 437 | Semantically Accurate Super-Resolution Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel architecture and domain-specific feature loss, allowing super-resolution to operate as a pre-processing step to increase the performance of downstream computer vision tasks, specifically semantic segmentation. |
Tristan Frizza; Donald G. Dansereau; Nagita Mehr Seresht; Michael Bewley; | arxiv-cs.CV | 2022-05-17 |
| 438 | Diffusion Models for Adversarial Purification Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we propose DiffPure that uses diffusion models for adversarial purification: Given an adversarial example, we first diffuse it with a small amount of noise following a forward diffusion process, and then recover the clean image through a reverse generative process. |
WEILI NIE et. al. | arxiv-cs.LG | 2022-05-16 |
| 439 | Transferability of Adversarial Attacks on Synthetic Speech Detection Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: 3) The effect of clipping or self-padding operation on the transferability of adversarial attacks. By performing these analyses, we summarise the weaknesses of synthetic speech detectors and the transferability behaviours of adversarial attacks, which provide insights for future research. |
Jiacheng Deng; Shunyi Chen; Li Dong; Diqun Yan; Rangding Wang; | arxiv-cs.SD | 2022-05-16 |
| 440 | Generation of Non-stationary Stochastic Fields Using Generative Adversarial Networks with Limited Training Data Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate the problem of training Generative Adversarial Networks (GANs) models against a dataset of geological channelized patterns that has a few non-stationary spatial modes and examine the training and self-conditioning settings that improve the generalization capability at new spatial modes that were never seen in the given training set. |
Alhasan Abdellatif; Ahmed H. Elsheikh; Daniel Busby; Philippe Berthet; | arxiv-cs.LG | 2022-05-11 |
| 441 | Alternative Data Augmentation for Industrial Monitoring Using Adversarial Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this article, a novel strategy is proposed to augment small image datasets. |
Silvan Mertes; Andreas Margraf; Steffen Geinitz; Elisabeth André; | arxiv-cs.CV | 2022-05-09 |
| 442 | Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To better exploit the powerful generative capability of GAN for real-world face SR, in this paper, we establish two independent degradation branches in the forward and backward cycle-consistent reconstruction processes, respectively, while the two processes share the same restoration branch. |
HAO HOU et. al. | arxiv-cs.CV | 2022-05-08 |
| 443 | End-to-End Rubbing Restoration Using Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose the RubbingGAN model for restoring incomplete rubbing characters. |
Gongbo Sun; Zijie Zheng; Ming Zhang; | arxiv-cs.CV | 2022-05-07 |
| 444 | Generative Adversarial Neural Operators Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we instantiate GANO using the Wasserstein criterion and show how the Wasserstein loss can be computed in infinite-dimensional spaces. |
Md Ashiqur Rahman; Manuel A. Florez; Anima Anandkumar; Zachary E. Ross; Kamyar Azizzadenesheli; | arxiv-cs.LG | 2022-05-06 |
| 445 | Text to Artistic Image Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Painting is one of the ways for people to express their ideas, but what if people with disabilities in hands want to paint? To tackle this challenge, we create an end-to-end solution that can generate artistic images from text descriptions. |
Qinghe Tian; Jean-Claude Franchitti; | arxiv-cs.CV | 2022-05-05 |
| 446 | Subverting Fair Image Search with Generative Adversarial Perturbations Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we explore the intersection fairness and robustness in the context of ranking: when a ranking model has been calibrated to achieve some definition of fairness, is it possible for an external adversary to make the ranking model behave unfairly without having access to the model or training data? |
Avijit Ghosh; Matthew Jagielski; Christo Wilson; | arxiv-cs.LG | 2022-05-04 |
| 447 | Wasserstein Adversarial Learning Based Temporal Knowledge Graph Embedding Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new temporal knowledge graph embedding framework by introducing adversarial learning to further refine the performance of traditional TKGE models. |
Yuanfei Dai; Wenzhong Guo; Carsten Eickhoff; | arxiv-cs.IR | 2022-05-03 |
| 448 | ARCADE: Adversarially Regularized Convolutional Autoencoder for Network Anomaly Detection Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a practical unsupervised anomaly-based deep learning detection system called ARCADE (Adversarially Regularized Convolutional Autoencoder for unsupervised network anomaly DEtection). |
Willian T. Lunardi; Martin Andreoni Lopez; Jean-Pierre Giacalone; | arxiv-cs.LG | 2022-05-03 |
| 449 | Splicing Detection and Localization In Satellite Imagery Using Conditional GANs IF:3 Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Satellite images specifically can be modified in a number of ways, including the insertion of objects to hide existing scenes and structures. In this paper, we describe the use of a Conditional Generative Adversarial Network (cGAN) to identify the presence of such spliced forgeries within satellite images. |
EMILY R. BARTUSIAK et. al. | arxiv-cs.CV | 2022-05-03 |
| 450 | Enhancing Adversarial Training with Feature Separability Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we observe two major shortcomings of the features learned by existing adversarial training methods:(1) low intra-class feature similarity; and (2) conservative inter-classes feature variance. To overcome these shortcomings, we introduce a new concept of adversarial training graph (ATG) with which the proposed adversarial training with feature separability (ATFS) enables to coherently boost the intra-class feature similarity and increase inter-class feature variance. |
Yaxin Li; Xiaorui Liu; Han Xu; Wentao Wang; Jiliang Tang; | arxiv-cs.CV | 2022-05-02 |
| 451 | Logically Consistent Adversarial Attacks for Soft Theorem Provers Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Recent efforts within the AI community have yielded impressive results towards soft theorem proving over natural language sentences using language models. We propose a novel, generative adversarial framework for probing and improving these models’ reasoning capabilities. |
Alexander Gaskell; Yishu Miao; Lucia Specia; Francesca Toni; | arxiv-cs.LG | 2022-04-29 |
| 452 | Curvature Graph Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we proposed a novel Curvature Graph Generative Adversarial Networks method, named CurvGAN, which is the first GAN-based graph representation method in the Riemannian geometric manifold. |
JIANXIN LI et. al. | www | 2022-04-29 |
| 453 | Generative Session-based Recommendation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Previous models mostly focus on designing different models to fit the observed data, which can be quite sparse in real-world scenarios. To alleviate this problem, in this paper, we propose a novel generative session-based recommendation framework. |
ZHIDAN WANG et. al. | www | 2022-04-29 |
| 454 | Semi-MoreGAN: A New Semi-supervised Generative Adversarial Network for Mixture of Rain Removal Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We observe that: (i) rain is a mixture of rain streaks and rainy haze; (ii) the scene depth determines the intensity of rain streaks and the transformation into the rainy haze; (iii) most existing deraining methods are only trained on synthetic rainy images, and hence generalize poorly to the real-world scenes. Motivated by these observations, we propose a new SEMI-supervised Mixture Of rain REmoval Generative Adversarial Network (Semi-MoreGAN), which consists of four key modules: (I) a novel attentional depth prediction network to provide precise depth estimation; (ii) a context feature prediction network composed of several well-designed detailed residual blocks to produce detailed image context features; (iii) a pyramid depth-guided non-local network to effectively integrate the image context with the depth information, and produce the final rain-free images; and (iv) a comprehensive semi-supervised loss function to make the model not limited to synthetic datasets but generalize smoothly to real-world heavy rainy scenes. |
YIYANG SHEN et. al. | arxiv-cs.CV | 2022-04-28 |
| 455 | Defending Person Detection Against Adversarial Patch Attack By Using Universal Defensive Frame Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel defense strategy that defends against an adversarial patch attack by optimizing a defensive frame for person detection. |
Youngjoon Yu; Hong Joo Lee; Hakmin Lee; Yong Man Ro; | arxiv-cs.CV | 2022-04-27 |
| 456 | Restricted Black-box Adversarial Attack Against DeepFake Face Swapping Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specially, we propose the Transferable Cycle Adversary Generative Adversarial Network (TCA-GAN) to construct the adversarial perturbation for disrupting unknown DeepFake systems. |
Junhao Dong; Yuan Wang; Jianhuang Lai; Xiaohua Xie; | arxiv-cs.CV | 2022-04-26 |
| 457 | Intercategorical Label Interpolation for Emotional Face Generation with Conditional Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This greatly hinders the learning and modeling of smooth transitions between displayed affective states. To overcome this challenge, we explore the potential of label interpolation to enhance networks trained on categorical datasets with the ability to generate images conditioned on continuous features. |
SILVAN MERTES et. al. | arxiv-cs.CV | 2022-04-26 |
| 458 | Self-recoverable Adversarial Examples: A New Effective Protection Mechanism in Social Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, the existing adversarial example does not have recoverability for serving as an effective protection mechanism. To address this issue, we propose a recoverable generative adversarial network to generate self-recoverable adversarial examples. |
Jiawei Zhang; Jinwei Wang; Hao Wang; Xiangyang Luo; | arxiv-cs.CV | 2022-04-25 |
| 459 | Evolutionary Latent Space Search for Driving Human Portrait Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This article presents an evolutionary approach for synthetic human portraits generation based on the latent space exploration of a generative adversarial network. |
Benjamín Machín; Sergio Nesmachnow; Jamal Toutouh; | arxiv-cs.CV | 2022-04-25 |
| 460 | When Adversarial Examples Are Excusable Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we analyze both test errors and adversarial errors on a well controlled but highly non-linear visual classification problem. |
Pieter-Jan Kindermans; Charles Staats; | arxiv-cs.LG | 2022-04-25 |
| 461 | A Note on The Regularity of Images Generated By Convolutional Neural Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Abstract: The regularity of images generated by convolutional neural networks, such as the U-net, generative adversarial networks, or the deep image prior, is analyzed. In a … |
Andreas Habring; Martin Holler; | arxiv-cs.CV | 2022-04-22 |
| 462 | 6GAN: IPv6 Multi-Pattern Target Generation Via Generative Adversarial Nets with Reinforcement Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we introduce 6GAN, a novel architecture built with Generative Adversarial Net (GAN) and reinforcement learning for multi-pattern target generation. |
TIANYU CUI et. al. | arxiv-cs.NI | 2022-04-20 |
| 463 | DAM-GAN : Image Inpainting Using Dynamic Attention Map Based on Fake Texture Detection Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To reduce pixel inconsistency disorder resulted from fake textures, we introduce a GAN-based model using dynamic attention map (DAM-GAN). |
Dongmin Cha; Daijin Kim; | arxiv-cs.CV | 2022-04-20 |
| 464 | CorrGAN: Input Transformation Technique Against Natural Corruptions Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose CorrGAN approach, which can generate benign input when a corrupted input is provided. |
Mirazul Haque; Christof J. Budnik; Wei Yang; | arxiv-cs.LG | 2022-04-18 |
| 465 | CgAT: Center-Guided Adversarial Training for Deep Hashing-Based Retrieval Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a min-max based Center-guided Adversarial Training, namely CgAT, to improve the robustness of deep hashing networks through worst adversarial examples. |
Xunguang Wang; Yinqun Lin; Xiaomeng Li; | arxiv-cs.CV | 2022-04-18 |
| 466 | DR-GAN: Distribution Regularization for Text-to-Image Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper presents a new Text-to-Image generation model, named Distribution Regularization Generative Adversarial Network (DR-GAN), to generate images from text descriptions from improved distribution learning. |
Hongchen Tan; Xiuping Liu; Baocai Yin; Xin Li; | arxiv-cs.CV | 2022-04-17 |
| 467 | SETTI: A Self-supervised Adversarial Malware Detection Architecture in An IoT Environment Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by this, in this paper we propose an adversarial self-supervised architecture for detecting malware in IoT networks, SETTI, considering samples of IoT network traffic that may not be labeled. |
Marjan Golmaryami; Rahim Taheri; Zahra Pooranian; Mohammad Shojafar; Pei Xiao; | arxiv-cs.CR | 2022-04-16 |
| 468 | Synthesizing Informative Training Samples with GAN Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a novel method to synthesize Informative Training samples with GAN (IT-GAN). |
Bo Zhao; Hakan Bilen; | arxiv-cs.LG | 2022-04-15 |
| 469 | PLGAN: Generative Adversarial Networks for Power-Line Segmentation in Aerial Images Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper presents PLGAN, a simple yet effective method based on generative adversarial networks, to segment power lines from aerial images with different backgrounds. |
Rabab Abdelfattah; Xiaofeng Wang; Song Wang; | arxiv-cs.CV | 2022-04-14 |
| 470 | Robotic and Generative Adversarial Attacks in Offline Writer-independent Signature Verification Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This study explores how robots and generative approaches can be used to mount successful false-acceptance adversarial attacks on signature verification systems. |
Jordan J. Bird; | arxiv-cs.RO | 2022-04-14 |
| 471 | Approximating Constraint Manifolds Using Generative Models for Sampling-Based Constrained Motion Planning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a learning-based sampling strategy for constrained motion planning problems. |
Cihan Acar; Keng Peng Tee; | arxiv-cs.RO | 2022-04-14 |
| 472 | Q-TART: Quickly Training for Adversarial Robustness and In-Transferability Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to simultaneously tackle Performance, Efficiency, and Robustness, using our proposed algorithm Q-TART, Quickly Train for Adversarial Robustness and in-Transferability. |
Madan Ravi Ganesh; Salimeh Yasaei Sekeh; Jason J. Corso; | arxiv-cs.CV | 2022-04-14 |
| 473 | Liuer Mihou: A Practical Framework for Generating and Evaluating Grey-box Adversarial Attacks Against NIDS Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents the Liuer Mihou attack that generates practical and replayable adversarial network packets that can bypass anomaly-based NIDS deployed in the Internet of Things (IoT) networks. |
KE HE et. al. | arxiv-cs.CR | 2022-04-12 |
| 474 | Generative Adversarial Networks for Image Augmentation in Agriculture: A Systematic Review Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper presents an overview of the evolution of GAN architectures followed by a systematic review of their application to agriculture (https://github.com/Derekabc/GANs-Agriculture), involving various vision tasks for plant health, weeds, fruits, aquaculture, animal farming, plant phenotyping as well as postharvest detection of fruit defects. |
Ebenezer Olaniyi; Dong Chen; Yuzhen Lu; Yanbo Huang; | arxiv-cs.CV | 2022-04-10 |
| 475 | SnapMode: An Intelligent and Distributed Large-Scale Fashion Image Retrieval Platform Based On Big Data and Deep Generative Adversarial Network Technologies Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The role of the proposed platform is then described in developing a disentangled feature extraction method by employing deep convolutional generative adversarial networks (DCGANs) for content-based image indexing and retrieval. |
Narges Norouzi; Reza Azmi; Sara Saberi Tehrani Moghadam; Maral Zarvani; | arxiv-cs.IR | 2022-04-08 |
| 476 | Single-level Adversarial Data Synthesis Based on Neural Tangent Kernels Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a new generative model called the generative adversarial NTK (GA-NTK) that has a single-level objective. |
Yu-Rong Zhang; Ruei-Yang Su; Sheng Yen Chou; Shan-Hung Wu; | arxiv-cs.LG | 2022-04-08 |
| 477 | Distributed Statistical Min-Max Learning in The Presence of Byzantine Agents Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our main contribution is to provide a crisp analysis of the proposed robust extra-gradient algorithm for smooth convex-concave and smooth strongly convex-strongly concave functions. |
Arman Adibi; Aritra Mitra; George J. Pappas; Hamed Hassani; | arxiv-cs.LG | 2022-04-06 |
| 478 | Instance Segmentation of Unlabeled Modalities Via Cyclic Segmentation GAN Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel Cyclic Segmentation Generative Adversarial Network (CySGAN) that conducts image translation and instance segmentation jointly using a unified framework. |
LEANDER LAUENBURG et. al. | arxiv-cs.CV | 2022-04-06 |
| 479 | Learning to Generate Realistic Noisy Images Via Pixel-level Noise-aware Adversarial Training Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Subsequently, we propose a novel framework, namely Pixel-level Noise-aware Generative Adversarial Network (PNGAN). |
YUANHAO CAI et. al. | arxiv-cs.CV | 2022-04-06 |
| 480 | Optimization Models and Interpretations for Three Types of Adversarial Perturbations Against Support Vector Machines Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the optimization models and the interpretations for three types of adversarial perturbations against support vector machines, including sample-adversarial perturbations (sAP), class-universal adversarial perturbations (cuAP) as well as universal adversarial perturbations (uAP). |
Wen Su; Qingna Li; Chunfeng Cui; | arxiv-cs.LG | 2022-04-06 |
| 481 | GAIL-PT: A Generic Intelligent Penetration Testing Framework with Generative Adversarial Imitation Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Addressing the challenges, for the first time, we introduce expert knowledge to guide the agent to make better decisions in RL-based PT and propose a Generative Adversarial Imitation Learning-based generic intelligent Penetration testing framework, denoted as GAIL-PT, to solve the problems of higher labor costs due to the involvement of security experts and high-dimensional discrete action space. |
Jinyin Chen; Shulong Hu; Haibin Zheng; Changyou Xing; Guomin Zhang; | arxiv-cs.CR | 2022-04-05 |
| 482 | DAD: Data-free Adversarial Defense at Test Time Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Also, data curation is expensive and companies may have proprietary rights over it. To handle such situations, we propose a completely novel problem of ‘test-time adversarial defense in absence of training data and even their statistics’. |
Gaurav Kumar Nayak; Ruchit Rawal; Anirban Chakraborty; | arxiv-cs.LG | 2022-04-04 |
| 483 | SHAIL: Safety-Aware Hierarchical Adversarial Imitation Learning for Autonomous Driving in Urban Environments Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: However, to scale to complex settings, many autonomous driving systems combine fixed, safe, optimization-based low-level controllers with high-level decision-making logic that selects the appropriate task and associated controller. In this paper, we attempt to bridge this gap in complexity by employing Safety-Aware Hierarchical Adversarial Imitation Learning (SHAIL), a method for learning a high-level policy that selects from a set of low-level controller instances in a way that imitates low-level driving data on-policy. |
Arec Jamgochian; Etienne Buehrle; Johannes Fischer; Mykel J. Kochenderfer; | arxiv-cs.RO | 2022-04-04 |
| 484 | Detecting In-vehicle Intrusion Via Semi-supervised Learning-based Convolutional Adversarial Autoencoders Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Although machine learning methods have many advantages for IDS, previous models usually require a large amount of labeled data, which results in high time and labor costs. To handle this problem, we propose a novel semi-supervised learning-based convolutional adversarial autoencoder model in this paper. |
Thien-Nu Hoang; Daehee Kim; | arxiv-cs.CR | 2022-04-03 |
| 485 | StyleWaveGAN: Style-based Synthesis of Drum Sounds with Extensive Controls Using Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we introduce StyleWaveGAN, a style-based drum sound generator that is a variation of StyleGAN, a state-of-the-art image generator. |
Antoine Lavault; Axel Roebel; Matthieu Voiry; | arxiv-cs.SD | 2022-04-02 |
| 486 | Adversarial Neon Beam: Robust Physical-World Adversarial Attack to DNNs Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an attack method called adversarial neon beam (AdvNB), which can execute the physical attack by obtaining the physical parameters of adversarial neon beams with very few queries. |
Chengyin Hu; Kalibinuer Tiliwalidi; | arxiv-cs.CV | 2022-04-02 |
| 487 | DAG-WGAN: Causal Structure Learning With Wasserstein Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a new model named DAG-WGAN, which combines the Wasserstein-based adversarial loss, an auto-encoder architecture together with an acyclicity constraint. |
Hristo Petkov; Colin Hanley; Feng Dong; | arxiv-cs.LG | 2022-04-01 |
| 488 | Fashion Style Generation: Evolutionary Search with Gaussian Mixture Models in The Latent Space Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper presents a novel approach for guiding a Generative Adversarial Network trained on the FashionGen dataset to generate designs corresponding to target fashion styles. |
Imke Grabe; Jichen Zhu; Manex Agirrezabal; | arxiv-cs.NE | 2022-04-01 |
| 489 | Adversarial Examples in Random Neural Networks with General Activations Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a result of the same type, with no restriction on width and for general locally Lipschitz continuous activations. |
Andrea Montanari; Yuchen Wu; | arxiv-cs.LG | 2022-03-31 |
| 490 | Synthesis and Execution of Communicative Robotic Movements with Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we focus on how to transfer on two different robotic platforms the same kinematics modulation that humans adopt when manipulating delicate objects, aiming to endow robots with the capability to show carefulness in their movements. |
LUCA GARELLO et. al. | arxiv-cs.RO | 2022-03-29 |
| 491 | Photographic Visualization of Weather Forecasts with Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We therefore introduce a novel method that uses photographic images to also visualize future weather conditions. |
Christian Sigg; Flavia Cavallaro; Tobias Günther; Martin R. Oswald; | arxiv-cs.CV | 2022-03-29 |
| 492 | Infrared and Visible Image Fusion Via Interactive Compensatory Attention Adversarial Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Toward this end, we propose a novel end-to-end mode based on generative adversarial training to achieve better fusion balance, termed as \textit{interactive compensatory attention fusion network} (ICAFusion). |
Zhishe Wang; Wenyu Shao; Yanlin Chen; Jiawei Xu; Xiaoqin Zhang; | arxiv-cs.CV | 2022-03-29 |
| 493 | Noise-robust Speech Recognition with 10 Minutes Unparalleled In-domain Data Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a generative adversarial network to simulate noisy spectrum from the clean spectrum (Simu-GAN), where only 10 minutes of unparalleled in-domain noisy speech data is required as labels. |
Chen Chen; Nana Hou; Yuchen Hu; Shashank Shirol; Eng Siong Chng; | arxiv-cs.SD | 2022-03-29 |
| 494 | TransductGAN: A Transductive Adversarial Model for Novelty Detection Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we propose TransductGAN, a transductive generative adversarial network that attempts to learn how to generate image examples from both the novel and negative classes by using a mixture of two Gaussians in the latent space. |
Najiba Toron; Janaina Mourao-Miranda; John Shawe-Taylor; | arxiv-cs.LG | 2022-03-29 |
| 495 | Treatment Learning Transformer for Noisy Image Classification Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we incorporate this binary information of existence of noise as treatment into image classification tasks to improve prediction accuracy by jointly estimating their treatment effects. |
Chao-Han Huck Yang; I-Te Danny Hung; Yi-Chieh Liu; Pin-Yu Chen; | arxiv-cs.CV | 2022-03-29 |
| 496 | Conjugate Gradient Method for Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Since this optimization is more difficult than minimization of a single objective function, we propose to apply the conjugate gradient method to solve the local Nash equilibrium problem in GANs. |
Hiroki Naganuma; Hideaki Iiduka; | arxiv-cs.LG | 2022-03-28 |
| 497 | A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologies Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a comprehensive survey trying to offer a systematic and structured investigation on robust adversarial training in pattern recognition. |
Zhuang Qian; Kaizhu Huang; Qiu-Feng Wang; Xu-Yao Zhang; | arxiv-cs.CV | 2022-03-26 |
| 498 | Reverse Engineering of Imperceptible Adversarial Image Perturbations Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: By integrating these RED principles with image denoising, we propose a new Class-Discriminative Denoising based RED framework, termed CDD-RED. |
YIFAN GONG et. al. | arxiv-cs.CV | 2022-03-26 |
| 499 | From MIM-Based GAN to Anomaly Detection:Event Probability Influence on Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce the exponential information metric into the GAN, referred to as MIM-based GAN, whose superior characteristics on data generation are discussed in theory. |
Rui She; Pingyi Fan; | arxiv-cs.LG | 2022-03-25 |
| 500 | Fast and Computationally Efficient Generative Adversarial Network Algorithm for Unmanned Aerial Vehicle-based Network Coverage Optimization Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Considering the tremendous potential of unmanned aerial vehicles in the future, we propose a new heuristic algorithm for coverage optimization. |
MAREK RUŽIČKA et. al. | arxiv-cs.LG | 2022-03-25 |
| 501 | A Unified Contrastive Energy-based Model for Understanding The Generative Ability of Adversarial Training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we demystify this phenomenon by developing a unified probabilistic framework, called Contrastive Energy-based Models (CEM). |
Yifei Wang; Yisen Wang; Jiansheng Yang; Zhouchen Lin; | arxiv-cs.LG | 2022-03-25 |
| 502 | HiFi++: A Unified Framework for Bandwidth Extension and Speech Enhancement Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Generative adversarial networks have recently demonstrated outstanding performance in neural vocoding outperforming best autoregressive and flow-based models. In this paper, we show that this success can be extended to other tasks of conditional audio generation. |
Pavel Andreev; Aibek Alanov; Oleg Ivanov; Dmitry Vetrov; | arxiv-cs.SD | 2022-03-24 |
| 503 | Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we propose a novel feature-level adversarial training method named FLAT. |
Hanjie Chen; Yangfeng Ji; | arxiv-cs.CL | 2022-03-23 |
| 504 | Dazzle: Using Optimized Generative Adversarial Networks to Address Security Data Class Imbalance Issue Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Method: We introduce an approach called Dazzle which is an optimized version of conditional Wasserstein Generative Adversarial Networks with gradient penalty (cWGAN-GP). |
Rui Shu; Tianpei Xia; Laurie Williams; Tim Menzies; | arxiv-cs.CR | 2022-03-21 |
| 505 | Review of Disentanglement Approaches for Medical Applications — Towards Solving The Gordian Knot of Generative Models in Healthcare Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we give a comprehensive overview of popular generative models, like Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Flow-based Models. |
Jana Fragemann; Lynton Ardizzone; Jan Egger; Jens Kleesiek; | arxiv-cs.LG | 2022-03-21 |
| 506 | FGAN: Federated Generative Adversarial Networks for Anomaly Detection in Network Traffic Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The solution proposed in this work aims at tackling the above two issues by using GANs in a federated architecture in networks of such scale and capacity. |
Sankha Das; | arxiv-cs.CR | 2022-03-21 |
| 507 | NeuralReshaper: Single-image Human-body Retouching with Deep Neural Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present NeuralReshaper, a novel method for semantic reshaping of human bodies in single images using deep generative networks. |
Beijia Chen; Hongbo Fu; Xiang Chen; Kun Zhou; Youyi Zheng; | arxiv-cs.CV | 2022-03-20 |
| 508 | Font Generation with Missing Impression Labels Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a font generation model that is robust against missing impression labels. |
Seiya Matsuda; Akisato Kimura; Seiichi Uchida; | arxiv-cs.CV | 2022-03-19 |
| 509 | Modelling Nonlinear Dependencies in The Latent Space of Inverse Scattering Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This motivates using models for this distribution that allow for non-linear dependencies between variables. |
Juliusz Ziomek; Katayoun Farrahi; | arxiv-cs.CV | 2022-03-19 |
| 510 | AutoAdversary: A Pixel Pruning Method for Sparse Adversarial Attack Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: From the perspective of neural network pruning, we propose a novel end-to-end sparse adversarial attack method, namely AutoAdversary, which can find the most important pixels automatically by integrating the pixel selection into the adversarial attack. |
Jinqiao Li; Xiaotao Liu; Jian Zhao; Furao Shen; | arxiv-cs.CV | 2022-03-18 |
| 511 | AdIoTack: Quantifying and Refining Resilience of Decision Tree Ensemble Inference Models Against Adversarial Volumetric Attacks on IoT Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present AdIoTack, a system that highlights vulnerabilities of decision trees against adversarial attacks, helping cybersecurity teams quantify and refine the resilience of their trained models for monitoring IoT networks. |
Arman Pashamokhtari; Gustavo Batista; Hassan Habibi Gharakheili; | arxiv-cs.LG | 2022-03-18 |
| 512 | Concept-based Adversarial Attacks: Tricking Humans and Classifiers Alike Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to generate adversarial samples by modifying activations of upper layers encoding semantically meaningful concepts. |
Johannes Schneider; Giovanni Apruzzese; | arxiv-cs.LG | 2022-03-18 |
| 513 | Fine Detailed Texture Learning for 3D Meshes with Generative Models Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a method to reconstruct high-quality textured 3D models from both multi-view and single-view images. |
Aysegul Dundar; Jun Gao; Andrew Tao; Bryan Catanzaro; | arxiv-cs.CV | 2022-03-17 |
| 514 | Image Super-Resolution With Deep Variational Autoencoders Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce VDVAE-SR, a new model that aims to exploit the most recent deep VAE methodologies to improve upon the results of similar models. |
Darius Chira; Ilian Haralampiev; Ole Winther; Andrea Dittadi; Valentin Liévin; | arxiv-cs.CV | 2022-03-17 |
| 515 | Generating Unrepresented Proportions of Geological Facies Using Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we investigate the capacity of Generative Adversarial Networks (GANs) in interpolating and extrapolating facies proportions in a geological dataset. |
Alhasan Abdellatif; Ahmed H. Elsheikh; Gavin Graham; Daniel Busby; Philippe Berthet; | arxiv-cs.LG | 2022-03-17 |
| 516 | On The Properties of Adversarially-Trained CNNs Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we describe surprising properties of adversarially-trained models, shedding light on mechanisms through which robustness against adversarial attacks is implemented. |
Mattia Carletti; Matteo Terzi; Gian Antonio Susto; | arxiv-cs.CV | 2022-03-17 |
| 517 | Robustness Through Cognitive Dissociation Mitigation in Contrastive Adversarial Training Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we introduce a novel neural network training framework that increases model’s adversarial robustness to adversarial attacks while maintaining high clean accuracy by combining contrastive learning (CL) with adversarial training (AT). |
Adir Rahamim; Itay Naeh; | arxiv-cs.LG | 2022-03-16 |
| 518 | Driving Anomaly Detection Using Conditional Generative Adversarial Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This study proposes an unsupervised method to quantify driving anomalies using a conditional generative adversarial network (GAN). |
Yuning Qiu; Teruhisa Misu; Carlos Busso; | arxiv-cs.CV | 2022-03-15 |
| 519 | Neural Radiance Projection Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The proposed method, Neural Radiance Projection (NeRP), addresses the three most fundamental shortages of training such a convolutional neural network on X-ray image segmentation: dealing with missing/limited human-annotated datasets; ambiguity on the per-pixel label; and the imbalance across positive- and negative- classes distribution. |
Pham Ngoc Huy; Tran Minh Quan; | arxiv-cs.CV | 2022-03-15 |
| 520 | Generating Privacy-Preserving Process Data with Deep Generative Models Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We introduced an adversarial generative network for process data generation (ProcessGAN) with two Transformer networks for the generator and the discriminator. |
Keyi Li; Sen Yang; Travis M. Sullivan; Randall S. Burd; Ivan Marsic; | arxiv-cs.LG | 2022-03-15 |
| 521 | A Review of Generative Adversarial Networks for Electronic Health Records: Applications, Evaluation Measures and Data Sources Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work aims to review the major developments in various applications of GANs for EHRs and provides an overview of the proposed methodologies. |
Ghadeer Ghosheh; Jin Li; Tingting Zhu; | arxiv-cs.LG | 2022-03-14 |
| 522 | On The Benefits of Knowledge Distillation for Adversarial Robustness Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To that end, we present Adversarial Knowledge Distillation (AKD), a new framework to improve a model’s robust performance, consisting on adversarially training a student on a mixture of the original labels and the teacher outputs. |
Javier Maroto; Guillermo Ortiz-Jiménez; Pascal Frossard; | arxiv-cs.LG | 2022-03-14 |
| 523 | Defending From Physically-Realizable Adversarial Attacks Through Internal Over-Activation Analysis Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work presents Z-Mask, a robust and effective strategy to improve the adversarial robustness of convolutional networks against physically-realizable adversarial attacks. |
Giulio Rossolini; Federico Nesti; Fabio Brau; Alessandro Biondi; Giorgio Buttazzo; | arxiv-cs.CV | 2022-03-14 |
| 524 | Generating Practical Adversarial Network Traffic Flows Using NIDSGAN Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we ask the practical question of whether real-world ML-based NIDS can be circumvented by crafted adversarial flows, and if so, how can they be created. |
BOLOR-ERDENE ZOLBAYAR et. al. | arxiv-cs.CR | 2022-03-13 |
| 525 | TurbuGAN: An Adversarial Learning Approach to Spatially-Varying Multiframe Blind Deconvolution with Applications to Imaging Through Turbulence Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a self-supervised and self-calibrating multi-shot approach to imaging through atmospheric turbulence, called TurbuGAN. |
Brandon Yushan Feng; Mingyang Xie; Christopher A. Metzler; | arxiv-cs.CV | 2022-03-13 |
| 526 | A Survey in Adversarial Defences and Robustness in NLP Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The proposed survey is an attempt to review different methods proposed for adversarial defenses in NLP in the recent past by proposing a novel taxonomy. |
Shreya Goyal; Sumanth Doddapaneni; Mitesh M. Khapra; Balaraman Ravindran; | arxiv-cs.CL | 2022-03-12 |
| 527 | Block-Sparse Adversarial Attack to Fool Transformer-Based Text Classifiers Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a gradient-based adversarial attack against transformer-based text classifiers. |
Sahar Sadrizadeh; Ljiljana Dolamic; Pascal Frossard; | arxiv-cs.CL | 2022-03-11 |
| 528 | A High-precision Self-supervised Monocular Visual Odometry in Foggy Weather Based on Robust Cycled Generative Adversarial Networks and Multi-task Learning Aided Depth Estimation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a high-precision self-supervised monocular VO, which is specifically designed for navigation in foggy weather. |
Xiuyuan Li; Jiangang Yu; Fengchao Li; Guowen An; | arxiv-cs.CV | 2022-03-09 |
| 529 | FragmGAN: Generative Adversarial Nets for Fragmentary Data Imputation and Prediction Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: By leveraging the structure of response patterns, we propose a unified and flexible framework based on Generative Adversarial Nets (GAN) to deal with fragmentary data imputation and label prediction at the same time. |
Fang Fang; Shenliao Bao; | arxiv-cs.LG | 2022-03-09 |
| 530 | Robust Federated Learning Against Adversarial Attacks for Speech Emotion Recognition Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel federated adversarial learning framework for protecting both data and deep neural networks. |
YI CHANG et. al. | arxiv-cs.SD | 2022-03-09 |
| 531 | On Generative Models As The Basis for Digital Twins Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: A framework is proposed for generative models as a basis for digital twins or mirrors of structures. |
G. Tsialiamanis; D. J. Wagg; N. Dervilis; K. Worden; | arxiv-cs.LG | 2022-03-08 |
| 532 | Regularized Training of Intermediate Layers for Generative Models for Inverse Problems Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: For both of these inversion algorithms, we introduce a new regularized GAN training algorithm and demonstrate that the learned generative model results in lower reconstruction errors across a wide range of under sampling ratios when solving compressed sensing, inpainting, and super-resolution problems. |
Sean Gunn; Jorio Cocola; Paul Hand; | arxiv-cs.LG | 2022-03-08 |
| 533 | Machine Learning in NextG Networks Via Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate their use in next-generation (NextG) communications within the context of cognitive networks to address i) spectrum sharing, ii) detecting anomalies, and iii) mitigating security attacks. |
Ender Ayanoglu; Kemal Davaslioglu; Yalin E. Sagduyu; | arxiv-cs.LG | 2022-03-08 |
| 534 | Adaptative Perturbation Patterns: Realistic Adversarial Learning for Robust Intrusion Detection Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This work establishes the fundamental constraint levels required to achieve realism and introduces the Adaptative Perturbation Pattern Method (A2PM) to fulfill these constraints in a gray-box setting. |
João Vitorino; Nuno Oliveira; Isabel Praça; | arxiv-cs.CR | 2022-03-08 |
| 535 | DATGAN: Integrating Expert Knowledge Into Deep Learning for Synthetic Tabular Data Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This article presents the Directed Acyclic Tabular GAN (DATGAN) to address these limitations by integrating expert knowledge in deep learning models for synthetic tabular data generation. |
Gael Lederrey; Tim Hillel; Michel Bierlaire; | arxiv-cs.LG | 2022-03-07 |
| 536 | GANSpiration: Balancing Targeted and Serendipitous Inspiration in User Interface Design with Style-Based Generative Adversarial Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these issues, we propose the GANSpiration approach that suggests design examples for both targeted and serendipitous inspiration, leveraging a style-based Generative Adversarial Network. |
Mohammad Amin Mozaffari; Xinyuan Zhang; Jinghui Cheng; Jin L. C. Guo; | arxiv-cs.HC | 2022-03-07 |
| 537 | Adversarial Texture for Fooling Person Detectors in The Physical World Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We propose a generative method, named Toroidal-Cropping-based Expandable Generative Attack (TC-EGA), to craft AdvTexture with repetitive structures. |
ZHANHAO HU et. al. | arxiv-cs.CV | 2022-03-07 |
| 538 | Semantic-Aware Latent Space Exploration for Face Image Restoration Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a semantic-aware latent space exploration method for image restoration (SAIR). |
Yanhui Guo; Fangzhou Luo; | arxiv-cs.CV | 2022-03-06 |
| 539 | Searching for Robust Neural Architectures Via Comprehensive and Reliable Evaluation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate the above problems, we propose a novel framework, called Auto Adversarial Attack and Defense (AAAD), where we employ neural architecture search methods, and four types of robustness evaluations are considered, including adversarial noise, natural noise, system noise and quantified metrics, thereby assisting in finding more robust architectures. |
JIALIANG SUN et. al. | arxiv-cs.LG | 2022-03-06 |
| 540 | Hybrid Deep Learning Model Using SPCAGAN Augmentation for Insider Threat Analysis Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a linear manifold learning-based generative adversarial network, SPCAGAN, that takes input from heterogeneous data sources and adds a novel loss function to train the generator to produce high-quality data that closely resembles the original data distribution. |
R G Gayathri; Atul Sajjanhar; Yong Xiang; | arxiv-cs.CR | 2022-03-05 |
| 541 | Learning Category-Level Generalizable Object Manipulation Policy Via Generative Adversarial Self-Imitation Learning from Demonstrations Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Despite the recent progress in reinforcement learning, it is still very challenging to learn a generalizable manipulation policy that can handle a category of geometrically diverse articulated objects. In this work, we tackle this category-level object manipulation policy learning problem via imitation learning in a task-agnostic manner, where we assume no handcrafted dense rewards but only a terminal reward. |
Hao Shen; Weikang Wan; He Wang; | arxiv-cs.RO | 2022-03-03 |
| 542 | On Generating Parametrised Structural Data Using Conditional Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the current work, with a view to confronting such issues, the generation of artificial data using a variation of the generative adversarial network (GAN) algorithm, is used. |
G. Tsialiamanis; D. J. Wagg; N. Dervilis; K. Worden; | arxiv-cs.LG | 2022-03-03 |
| 543 | Detecting High-Quality GAN-Generated Face Images Using Neural Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this chapter, we propose a new strategy to differentiate GAN-generated images from authentic images by leveraging spectral band discrepancies, focusing on artificial face image synthesis. |
Ehsan Nowroozi; Mauro Conti; Yassine Mekdad; | arxiv-cs.CR | 2022-03-03 |
| 544 | Fail-Safe Generative Adversarial Imitation Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: For flexible yet safe imitation learning (IL), we propose a modular approach that uses a generative imitator policy with a safety layer, has an overall explicit density/gradient, can therefore be end-to-end trained using generative adversarial IL (GAIL), and comes with theoretical worst-case safety/robustness guarantees. |
Philipp Geiger; Christoph-Nikolas Straehle; | arxiv-cs.LG | 2022-03-03 |
| 545 | Discriminating Against Unrealistic Interpolations in Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we establish that the discriminator can be used effectively to avoid regions of low sample quality along shortest paths. |
Henning Petzka; Ted Kronvall; Cristian Sminchisescu; | arxiv-cs.LG | 2022-03-02 |
| 546 | On The Application of Generative Adversarial Networks for Nonlinear Modal Analysis Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the current work, a machine learning scheme is proposed with a view to performing nonlinear modal analysis. |
G. Tsialiamanis; M. D. Champneys; N. Dervilis; D. J. Wagg; K. Worden; | arxiv-cs.LG | 2022-03-02 |
| 547 | PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsampling Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a generative adversarial network for point cloud upsampling, which can not only make the upsampled points evenly distributed on the underlying surface but also efficiently generate clean high frequency regions. |
Hao Liu; Hui Yuan; Junhui Hou; Raouf Hamzaoui; Wei Gao; | arxiv-cs.CV | 2022-03-02 |
| 548 | Generative Adversarial Networks IF:2 Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We focus on these three issues: (1) mode collapse, (2) vanishing gradients, and (3) generation of low-quality images. |
Gilad Cohen; Raja Giryes; | arxiv-cs.CV | 2022-03-01 |
| 549 | MRI-GAN: A Generalized Approach to Detect DeepFakes Using Perceptual Image Assessment Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we describe our work to develop general, deep learning-based models to classify DeepFake content. |
Pratikkumar Prajapati; Chris Pollett; | arxiv-cs.CV | 2022-02-28 |
| 550 | Domain Disentangled Generative Adversarial Network for Zero-Shot Sketch-Based 3D Shape Retrieval Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel domain disentangled generative adversarial network (DD-GAN) for zero-shot sketch-based 3D retrieval, which can retrieve the unseen categories that are not accessed during training. |
Rui Xu; Zongyan Han; Le Hui; Jianjun Qian; Jin Xie; | arxiv-cs.CV | 2022-02-24 |
| 551 | Art Creation with Multi-Conditional StyleGANs Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a multi-conditional Generative Adversarial Network (GAN) approach trained on large amounts of human paintings to synthesize realistic-looking paintings that emulate human art. |
KONSTANTIN DOBLER et. al. | arxiv-cs.CV | 2022-02-23 |
| 552 | Generating Synthetic Mobility Networks with Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this article, we address mobility network generation, i.e., generating a city’s entire mobility network, a weighted directed graph in which nodes are geographic locations and weighted edges represent people’s movements between those locations, thus describing the entire mobility set flows within a city. |
Giovanni Mauro; Massimiliano Luca; Antonio Longa; Bruno Lepri; Luca Pappalardo; | arxiv-cs.LG | 2022-02-22 |
| 553 | Social Computational Design Method for Generating Product Shapes with GAN and Transformer Models Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: A social computational design method is established, aiming at taking advantages of the fast-developing artificial intelligence technologies for intelligent product design. |
Maolin Yang; Pingyu Jiang; | arxiv-cs.AI | 2022-02-22 |
| 554 | Synthetic CT Skull Generation for Transcranial MR Imaging-Guided Focused Ultrasound Interventions with Conditional Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We compared the performance of synthetic CT to real CT images using Kranion and k-Wave acoustic simulation. |
HAN LIU et. al. | arxiv-cs.CV | 2022-02-21 |
| 555 | Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we found that the recent emerging paradigm of implicit neural representations (INRs) that encodes a continuous signal into a parameterized neural network effectively mitigates the issue. |
SIHYUN YU et. al. | arxiv-cs.CV | 2022-02-21 |
| 556 | GAN-DUF: Hierarchical Deep Generative Models for Design Under Free-Form Geometric Uncertainty Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Past work that quantifies such uncertainty often makes simplifying assumptions on geometric variations, while the real-world, free-form uncertainty and its impact on design performance are difficult to quantify due to the high dimensionality. To address this issue, we propose a Generative Adversarial Network-based Design under Uncertainty Framework (GAN-DUF), which contains a deep generative model that simultaneously learns a compact representation of nominal (ideal) designs and the conditional distribution of fabricated designs given any nominal design. |
Wei Wayne Chen; Doksoo Lee; Oluwaseyi Balogun; Wei Chen; | arxiv-cs.CE | 2022-02-21 |
| 557 | Transferring Adversarial Robustness Through Robust Representation Matching Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose Robust Representation Matching (RRM), a low-cost method to transfer the robustness of an adversarially trained model to a new model being trained for the same task irrespective of architectural differences. |
Pratik Vaishnavi; Kevin Eykholt; Amir Rahmati; | arxiv-cs.LG | 2022-02-21 |
| 558 | Holistic Attention-Fusion Adversarial Network for Single Image Defogging Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Adversarial learning-based image defogging methods have been extensively studied in computer vision due to their remarkable performance. |
Wei Liu; Cheng Chen; Rui Jiang; Tao Lu; Zixiang Xiong; | arxiv-cs.CV | 2022-02-19 |
| 559 | PerFED-GAN: Personalized Federated Learning Via Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a federated learning method based on co-training and generative adversarial networks(GANs) that allows each client to design its own model to participate in federated learning training independently without sharing any model architecture or parameter information with other clients or a center. |
Xingjian Cao; Gang Sun; Hongfang Yu; Mohsen Guizani; | arxiv-cs.LG | 2022-02-18 |
| 560 | Fast Online Inference for Nonlinear Contextual Bandit Based on Generative Adversarial Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a neural bandit model with an end-to-end training process to efficiently perform bandit algorithms such as Thompson Sampling and UCB during inference. |
Yun Da Tsai; Shou De Lin; | arxiv-cs.LG | 2022-02-17 |
| 561 | Point Cloud Generation with Continuous Conditioning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Generative models can be used to synthesize 3D objects of high quality and diversity. |
Larissa T. Triess; Andre Bühler; David Peter; Fabian B. Flohr; J. Marius Zöllner; | arxiv-cs.CV | 2022-02-17 |
| 562 | The Adversarial Security Mitigations of MmWave Beamforming Prediction Models Using Defensive Distillation and Adversarial Retraining Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents the security vulnerabilities in deep learning for beamforming prediction using deep neural networks (DNNs) in 6G wireless networks, which treats the beamforming prediction as a multi-output regression problem. |
Murat Kuzlu; Ferhat Ozgur Catak; Umit Cali; Evren Catak; Ozgur Guler; | arxiv-cs.CR | 2022-02-16 |
| 563 | Deep Generative Model with Hierarchical Latent Factors for Time Series Anomaly Detection Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This work presents DGHL, a new family of generative models for time series anomaly detection, trained by maximizing the observed likelihood by posterior sampling and alternating back-propagation. |
Cristian Challu; Peihong Jiang; Ying Nian Wu; Laurent Callot; | arxiv-cs.LG | 2022-02-15 |
| 564 | Applying Adversarial Networks to Increase The Data Efficiency and Reliability of Self-Driving Cars Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The Adversarial Self-driving framework is applied to an image classification algorithm to improve the classification accuracy on perturbed images and is later applied to train a self-driving car to drive in a simulation. |
Aakash Kumar; | arxiv-cs.CV | 2022-02-15 |
| 565 | Generative Adversarial Network-Driven Detection of Adversarial Tasks in Mobile Crowdsensing Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: With this in mind, this paper aims to detect intelligently designed illegitimate sensing service requests by integrating a GAN-based model. |
Zhiyan Chen; Burak Kantarci; | arxiv-cs.CR | 2022-02-15 |
| 566 | Random Walks for Adversarial Meshes Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper proposes a novel, unified, and general adversarial attack, which leads to misclassification of numerous state-of-the-art mesh classification neural networks. |
Amir Belder; Gal Yefet; Ran Ben Izhak; Ayellet Tal; | arxiv-cs.CV | 2022-02-15 |
| 567 | Artificial Intelligence-Based Smart Grid Vulnerabilities and Potential Solutions for Fake-Normal Attacks: A Short Review Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The purpose of this short review is to outline some of the initiatives to protect smart grid systems, their obstacles, and what might be a potential future AI research direction |
J. D. Ndibwile; | arxiv-cs.CR | 2022-02-14 |
| 568 | GAN-generated Faces Detection: A Survey and New Perspectives (2022) Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim to provide a comprehensive review of recent progress in GAN-face detection. |
Xin Wang; Hui Guo; Shu Hu; Ming-Ching Chang; Siwei Lyu; | arxiv-cs.CV | 2022-02-14 |
| 569 | Universal Adversarial Examples in Remote Sensing: Methodology and Benchmark Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this study, we systematically analyze the universal adversarial examples in remote sensing data for the first time, without any knowledge from the victim model. Specifically, we propose a novel black-box adversarial attack method, namely Mixup-Attack, and its simple variant Mixcut-Attack, for remote sensing data. |
Yonghao Xu; Pedram Ghamisi; | arxiv-cs.CV | 2022-02-14 |
| 570 | Finding Dynamics Preserving Adversarial Winning Tickets Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Pruning methods have been considered in adversarial context to reduce model capacity and improve adversarial robustness simultaneously in training. |
Xupeng Shi; Pengfei Zheng; A. Adam Ding; Yuan Gao; Weizhong Zhang; | arxiv-cs.LG | 2022-02-14 |
| 571 | Sim-to-Real Domain Adaptation for Lane Detection and Classification in Autonomous Driving Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose UDA schemes using adversarial discriminative and generative methods for lane detection and classification applications in autonomous driving. |
CHUQING HU et. al. | arxiv-cs.CV | 2022-02-14 |
| 572 | Do Inpainting Yourself: Generative Facial Inpainting Guided By Exemplars Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present EXE-GAN, a novel exemplar-guided facial inpainting framework using generative adversarial networks. |
WANGLONG LU et. al. | arxiv-cs.CV | 2022-02-13 |
| 573 | Domain-Invariant Proposals Based on A Balanced Domain Classifier for Object Detection Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we build domain-invariant detectors by learning domain classifiers via adversarial training. |
ZHIZE WU et. al. | arxiv-cs.CV | 2022-02-11 |
| 574 | Improving Image-recognition Edge Caches with A Generative Adversarial Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work shows that a well-known generative adversarial network, called ToDayGAN, can solve this problem by generating daytime images using nighttime ones. |
Guilherme B. Souza; Roberto G. Pacheco; Rodrigo S. Couto; | arxiv-cs.NI | 2022-02-11 |
| 575 | Open-set Adversarial Defense with Clean-Adversarial Mutual Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper proposes an Open-Set Defense Network with Clean-Adversarial Mutual Learning (OSDN-CAML) as a solution to the OSAD problem. |
Rui Shao; Pramuditha Perera; Pong C. Yuen; Vishal M. Patel; | arxiv-cs.CV | 2022-02-11 |
| 576 | STG-GAN: A Spatiotemporal Graph Generative Adversarial Networks for Short-term Passenger Flow Prediction in Urban Rail Transit Systems Literature Review Related Patents Related Grants Related Orgs Related Experts Details Hi |