v1v2 (latest)

Understanding and Improving Fast Adversarial Training

6 July 2020

Maksym Andriushchenko

Nicolas Flammarion

AAML

ArXiv (abs)PDF HTML Github (95★)

Papers citing "Understanding and Improving Fast Adversarial Training"

50 / 200 papers shown

Title
Mitigating Feature Gap for Adversarial Robustness by Feature Disentanglement Nuoyan Zhou Dawei Zhou Decheng Liu Xinbo Gao Nannan Wang AAML 161 0 0 26 Jan 2024
Efficient local linearity regularization to overcome catastrophic overfittingInternational Conference on Learning Representations (ICLR), 2024 Elias Abad Rocamora Fanghui Liu Grigorios G. Chrysos Pablo M. Olmos Volkan Cevher AAML 172 7 0 21 Jan 2024
Rethinking PGD Attack: Is Sign Function Necessary? Junjie Yang Tianlong Chen Xuxi Chen Zinan Lin Yingbin Liang AAML 237 2 0 03 Dec 2023
Relationship between Model Compression and Adversarial Robustness: A Review of Current EvidenceIEEE Symposium Series on Computational Intelligence (IEEE-SSCI), 2023 Svetlana Pavlitska Hannes Grolig J. Marius Zöllner AAML 210 5 0 27 Nov 2023
Towards Robust and Accurate Visual Prompting Qi Li Liangzhi Li Zhouqiang Jiang Bowen Wang VPVLM VLM 164 4 0 18 Nov 2023
Fast Propagation is Better: Accelerating Single-Step Adversarial Training via Sampling SubnetworksIEEE Transactions on Information Forensics and Security (IEEE TIFS), 2023 Yang Liu Jianshu Li Jindong Gu Yang Bai Xiaochun Cao AAML 184 14 0 24 Oct 2023
Learn from the Past: A Proxy Guided Adversarial Defense Framework with Self Distillation Regularization Yaohua Liu Jiaxin Gao Xianghao Jiao Zhu Liu Xin-Yue Fan Risheng Liu AAML 268 0 0 19 Oct 2023
SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models Boyang Zhang Zheng Li Ziqing Yang Xinlei He Michael Backes Mario Fritz Yang Zhang 317 8 0 19 Oct 2023
IRAD: Implicit Representation-driven Image Resampling against Adversarial AttacksInternational Conference on Learning Representations (ICLR), 2023 Yue Cao Tianlin Li Xiaofeng Cao Ivor Tsang Yang Liu Qing Guo AAML 237 4 0 18 Oct 2023
On the Over-Memorization During Natural, Robust and Catastrophic OverfittingInternational Conference on Learning Representations (ICLR), 2023 Runqi Lin Chaojian Yu Bo Han Tongliang Liu 215 16 0 13 Oct 2023
Generating Less Certain Adversarial Examples Improves Robust Generalization Minxing Zhang Michael Backes Xiao Zhang AAML 501 1 0 06 Oct 2023
Splitting the Difference on Adversarial TrainingUSENIX Security Symposium (USENIX Security), 2023 Matan Levi A. Kontorovich 223 8 0 03 Oct 2023
Improving Machine Learning Robustness via Adversarial TrainingInternational Conference on Computer Communications and Networks (ICCCN), 2023 Long Dang T. Hapuarachchi Kaiqi Xiong Jing Lin OOD AAML 134 4 0 22 Sep 2023
Robust and Efficient Interference Neural Networks for Defending Against Adversarial Attacks in ImageNet Yunuo Xiong Shujuan Liu H. Xiong AAML 116 0 0 03 Sep 2023
Fast Adversarial Training with Smooth ConvergenceIEEE International Conference on Computer Vision (ICCV), 2023 Mengnan Zhao Lulu Zhang Yuqiu Kong Baocai Yin AAML 125 11 0 24 Aug 2023
Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight AveragingIEEE Transactions on Information Forensics and Security (IEEE TIFS), 2023 Yang Liu YueFeng Chen Xiaofeng Mao Ranjie Duan Jindong Gu Rong Zhang H. Xue Xiaochun Cao AAML 193 13 0 22 Aug 2023
Adversarial Collaborative Filtering for FreeACM Conference on Recommender Systems (RecSys), 2023 Huiyuan Chen Xiaoting Li Vivian Lai Chin-Chia Michael Yeh Yujie Fan Yan Zheng Mahashweta Das Hao Yang AAML 119 8 0 20 Aug 2023
Robust Mixture-of-Expert Training for Convolutional Neural NetworksIEEE International Conference on Computer Vision (ICCV), 2023 Yihua Zhang Ruisi Cai Tianlong Chen Guanhua Zhang Huan Zhang Pin-Yu Chen Shiyu Chang Zinan Lin Sijia Liu MoE AAML OOD 151 31 0 19 Aug 2023
SoK: Realistic Adversarial Attacks and Defenses for Intelligent Network Intrusion DetectionComputers & security (Comput. Secur.), 2023 João Vitorino Isabel Praça Eva Maia AAML 184 29 0 13 Aug 2023
On the Interplay of Convolutional Padding and Adversarial Robustness Paul Gavrikov J. Keuper AAML 234 4 0 12 Aug 2023
An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine LearningIEEE Signal Processing Magazine (IEEE Signal Process. Mag.), 2023 Yihua Zhang Prashant Khanduri Ioannis C. Tsaknakis Yuguang Yao Min-Fong Hong Sijia Liu AI4CE 329 46 0 01 Aug 2023
Doubly Robust Instance-Reweighted Adversarial TrainingInternational Conference on Learning Representations (ICLR), 2023 Daouda Sow Sen-Fon Lin Zinan Lin Yitao Liang AAML OOD 268 2 0 01 Aug 2023
Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned FeaturesNeural Information Processing Systems (NeurIPS), 2023 Mingli Zhu Shaokui Wei H. Zha Baoyuan Wu AAML 178 49 0 29 Jun 2023
Group-based Robustness: A General Framework for Customized Robustness in the Real WorldNetwork and Distributed System Security Symposium (NDSS), 2023 Weiran Lin Keane Lucas Neo Eyal Lujo Bauer Michael K. Reiter Mahmood Sharif OOD AAML 232 1 0 29 Jun 2023
DSRM: Boost Textual Adversarial Training with Distribution Shift Risk MinimizationAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 Songyang Gao Jiajun Sun Yan Liu Xiao Wang Qi Zhang Zhongyu Wei Jin Ma Yingchun Shan OOD 156 9 0 27 Jun 2023
A Spectral Perspective towards Understanding and Improving Adversarial Robustness Binxiao Huang Rui Lin Chaofan Tao Ngai Wong AAML 131 0 0 25 Jun 2023
Revisiting and Advancing Adversarial Training Through A Simple Baseline Hong Liu AAML 202 0 0 13 Jun 2023
AROID: Improving Adversarial Robustness through Online Instance-wise Data AugmentationInternational Journal of Computer Vision (IJCV), 2023 Lin Li Jianing Qiu Michael W. Spratling AAML 140 8 0 12 Jun 2023
AdvFunMatch: When Consistent Teaching Meets Adversarial Robustness Ziuhi Wu Haichang Gao Bingqian Zhou Ping Wang AAML 191 0 0 24 May 2023
$Releasing Inequality Phenomenon in $\ell_{\infty}$-norm Adversarial Training via Input Gradient Distillation$ Releasing Inequality Phenomenon in $\ell_{\infty}$ -norm Adversarial Training via Input Gradient DistillationIEEE Transactions on Information Forensics and Security (IEEE TIFS), 2023 Junxi Chen Junhao Dong Xiaohua Xie Jianhuang Lai AAML 213 0 0 16 May 2023
Exploiting Frequency Spectrum of Adversarial Images for General Robustness Chun Yang Tan K. Kawamoto Hiroshi Kera AAML OOD 121 1 0 15 May 2023
Efficient Search of Comprehensively Robust Neural Architectures via Multi-fidelity EvaluationPattern Recognition (Pattern Recogn.), 2023 Jialiang Sun Wen Yao Tingsong Jiang Xiaoqian Chen AAML 162 12 0 12 May 2023
Cross-Entropy Loss Functions: Theoretical Analysis and ApplicationsInternational Conference on Machine Learning (ICML), 2023 Anqi Mao M. Mohri Yutao Zhong AAML 275 608 0 14 Apr 2023
Hyper-parameter Tuning for Adversarially Robust Models Pedro Mendes Paolo Romano David Garlan AAML 172 2 0 05 Apr 2023
Improving Fast Adversarial Training with Prior-Guided KnowledgeIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023 Yang Liu Yong Zhang Xingxing Wei Baoyuan Wu Ke Ma Jue Wang Xiaochun Cao AAML 226 45 0 01 Apr 2023
Adversarial Attack and Defense for Medical Image Analysis: Methods and ApplicationsACM Computing Surveys (ACM Comput. Surv.), 2023 Junhao Dong Junxi Chen Xiaohua Xie Jianhuang Lai Hechang Chen AAML MedIm 307 10 0 24 Mar 2023
Improved Adversarial Training Through Adaptive Instance-wise Loss Smoothing Lin Li Michael W. Spratling AAML 296 4 0 24 Mar 2023
PRISE: Demystifying Deep Lucas-Kanade with Strongly Star-Convex Constraints for Multimodel Image AlignmentComputer Vision and Pattern Recognition (CVPR), 2023 Yiqing Zhang Xinming Huang Ziming Zhang 157 9 0 21 Mar 2023
Improving the Robustness of Deep Convolutional Neural Networks Through Feature Learning Jin Ding Jie-Chao Zhao Yongyang Sun Ping Tan Ji-en Ma You-tong Fang AAML 99 1 0 11 Mar 2023
Less is More: Data Pruning for Faster Adversarial Training Yize Li Pu Zhao Xinyu Lin B. Kailkhura Ryan Goldh AAML 257 14 0 23 Feb 2023
Investigating Catastrophic Overfitting in Fast Adversarial Training: A Self-fitting Perspective Zhengbao He Tao Li Sizhe Chen Xiaolin Huang AAML 176 4 0 23 Feb 2023
Regret-Based Defense in Adversarial Reinforcement LearningAdaptive Agents and Multi-Agent Systems (AAMAS), 2023 Roman Belaire Pradeep Varakantham Thanh Nguyen David Lo AAML 251 3 0 14 Feb 2023
Better Diffusion Models Further Improve Adversarial TrainingInternational Conference on Machine Learning (ICML), 2023 Zekai Wang Tianyu Pang Chao Du Min Lin Weiwei Liu Shuicheng Yan DiffM 399 278 0 09 Feb 2023
Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset SelectionNeural Information Processing Systems (NeurIPS), 2023 Xilie Xu Jingfeng Zhang Yifan Zhang Masashi Sugiyama Mohan S. Kankanhalli AAML 424 21 0 08 Feb 2023
Towards Adversarial Realism and Robust Learning for IoT Intrusion Detection and Classification João Vitorino Isabel Praça Eva Maia AAML 263 32 0 30 Jan 2023
Data Augmentation Alone Can Improve Adversarial TrainingInternational Conference on Learning Representations (ICLR), 2023 Lin Li Michael W. Spratling 165 63 0 24 Jan 2023
RobArch: Designing Robust Architectures against Adversarial Attacks Sheng-Hsuan Peng Weilin Xu Cory Cornelius Kevin Wenliang Li Rahul Duggal Duen Horng Chau Jason Martin AAML 170 8 0 08 Jan 2023
Explainability and Robustness of Deep Visual Classification Models Jindong Gu AAML 224 2 0 03 Jan 2023
Alternating Objectives Generates Stronger PGD-Based Adversarial Attacks Nikolaos Antoniou Efthymios Georgiou Alexandros Potamianos AAML 165 5 0 15 Dec 2022
REAP: A Large-Scale Realistic Adversarial Patch BenchmarkIEEE International Conference on Computer Vision (ICCV), 2022 Nabeel Hingun Chawin Sitawarin Jerry Li David Wagner AAML 292 23 0 12 Dec 2022