Why adversarial training can hurt robust accuracy

3 March 2022

Papers citing "Why adversarial training can hurt robust accuracy"

50 / 52 papers shown

Title
Approximate Nullspace Augmented Finetuning for Robust Vision Transformers Haoyang Liu Aditya Singh Yijiang Li Haohan Wang AAML ViT 76 1 0 15 Mar 2024
Specification Overfitting in Artificial Intelligence Benjamin Roth Pedro Henrique Luz de Araujo Yuxi Xia Saskia Kaltenbrunner Christoph Korab 129 1 0 13 Mar 2024
Adversarial training with informed data selection Marcele O. K. Mendonça Javier Maroto P. Frossard P. Diniz AAML 21 4 0 07 Jan 2023
Interpolation can hurt robust generalization even when there is no noise Konstantin Donhauser Alexandru cTifrea Michael Aerni Reinhard Heckel Fanny Yang 57 14 0 05 Aug 2021
Data Quality Matters For Adversarial Training: An Empirical Study Chengyu Dong Liyuan Liu Jingbo Shang AAML 27 10 0 15 Feb 2021
Adversarial Perturbations Are Not So Weird: Entanglement of Robust and Non-Robust Features in Neural Network Classifiers Jacob Mitchell Springer Melanie Mitchell Garrett Kenyon AAML 42 13 0 09 Feb 2021
Recent Advances in Adversarial Training for Adversarial Robustness Tao Bai Jinqi Luo Jun Zhao Bihan Wen Qian Wang AAML 96 485 0 02 Feb 2021
Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks Wei-An Lin Chun Pong Lau Alexander Levine Ramalingam Chellappa Soheil Feizi AAML 81 60 0 05 Sep 2020
How benign is benign overfitting? Amartya Sanyal P. Dokania Varun Kanade Philip Torr NoLa AAML 34 57 0 08 Jul 2020
Understanding and Improving Fast Adversarial Training Maksym Andriushchenko Nicolas Flammarion AAML 53 286 0 06 Jul 2020
Improving robustness against common corruptions by covariate shift adaptation Steffen Schneider E. Rusak L. Eck Oliver Bringmann Wieland Brendel Matthias Bethge VLM 62 476 0 30 Jun 2020
Perceptual Adversarial Robustness: Defense Against Unseen Threat Models Cassidy Laidlaw Sahil Singla Soheil Feizi AAML OOD 51 185 0 22 Jun 2020
On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them Chen Liu Mathieu Salzmann Tao R. Lin Ryota Tomioka Sabine Süsstrunk AAML 75 81 0 15 Jun 2020
Provable tradeoffs in adversarially robust classification Yan Sun Hamed Hassani David Hong Alexander Robey 33 55 0 09 Jun 2020
Towards Understanding Fast Adversarial Training Bai Li Shiqi Wang Suman Jana Lawrence Carin AAML 39 50 0 04 Jun 2020
Breaking certified defenses: Semantic adversarial examples with spoofed robustness certificates Amin Ghiasi Ali Shafahi Tom Goldstein 51 55 0 19 Mar 2020
Adversarial Vertex Mixup: Toward Better Adversarially Robust Generalization Saehyung Lee Hyungyu Lee Sungroh Yoon AAML 184 113 0 05 Mar 2020
Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks Francesco Croce Matthias Hein AAML 194 1,821 0 03 Mar 2020
Overfitting in adversarially robust deep learning Leslie Rice Eric Wong Zico Kolter 73 796 0 26 Feb 2020
Understanding and Mitigating the Tradeoff Between Robustness and Accuracy Aditi Raghunathan Sang Michael Xie Fanny Yang John C. Duchi Percy Liang AAML 80 226 0 25 Feb 2020
Precise Tradeoffs in Adversarial Training for Linear Regression Adel Javanmard Mahdi Soltanolkotabi Hamed Hassani AAML 27 106 0 24 Feb 2020
CAT: Customized Adversarial Training for Improved Robustness Minhao Cheng Qi Lei Pin-Yu Chen Inderjit Dhillon Cho-Jui Hsieh OOD AAML 57 115 0 17 Feb 2020
More Data Can Expand the Generalization Gap Between Adversarially Robust and Standard Models Lin Chen Yifei Min Mingrui Zhang Amin Karbasi OOD 53 64 0 11 Feb 2020
Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss Lénaïc Chizat Francis R. Bach MLT 66 336 0 11 Feb 2020
Fast is better than free: Revisiting adversarial training Eric Wong Leslie Rice J. Zico Kolter AAML OOD 120 1,167 0 12 Jan 2020
Adversarial Domain Adaptation with Domain Mixup Minghao Xu Jian Zhang Bingbing Ni Teng Li Chengjie Wang Qi Tian Wenjun Zhang 41 446 0 04 Dec 2019
Towards Large yet Imperceptible Adversarial Image Perturbations with Perceptual Color Distance Zhengyu Zhao Zhuoran Liu Martha Larson AAML 34 143 0 06 Nov 2019
Instance adaptive adversarial training: Improved accuracy tradeoffs in neural nets Yogesh Balaji Tom Goldstein Judy Hoffman AAML 159 103 0 17 Oct 2019
Defending Against Physically Realizable Attacks on Image Classification Tong Wu Liang Tong Yevgeniy Vorobeychik AAML 53 126 0 20 Sep 2019
Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy Alex Lamb Vikas Verma Kenji Kawaguchi Alexander Matyasko Savya Khosla Arno Solin Yoshua Bengio AAML 42 99 0 16 Jun 2019
Adversarially Robust Generalization Just Requires More Unlabeled Data Runtian Zhai Tianle Cai Di He Chen Dan Kun He John E. Hopcroft Liwei Wang 61 156 0 03 Jun 2019
Unlabeled Data Improves Adversarial Robustness Y. Carmon Aditi Raghunathan Ludwig Schmidt Percy Liang John C. Duchi 98 752 0 31 May 2019
Are Labels Required for Improving Adversarial Robustness? J. Uesato Jean-Baptiste Alayrac Po-Sen Huang Robert Stanforth Alhussein Fawzi Pushmeet Kohli AAML 56 333 0 31 May 2019
Adversarial Examples Are Not Bugs, They Are Features Andrew Ilyas Shibani Santurkar Dimitris Tsipras Logan Engstrom Brandon Tran Aleksander Madry SILM 80 1,825 0 06 May 2019
Transfer of Adversarial Robustness Between Perturbation Types Daniel Kang Yi Sun Tom B. Brown Dan Hendrycks Jacob Steinhardt AAML 47 49 0 03 May 2019
Uniform convergence may be unable to explain generalization in deep learning Vaishnavh Nagarajan J. Zico Kolter MoMe AI4CE 46 314 0 13 Feb 2019
Theoretically Principled Trade-off between Robustness and Accuracy Hongyang R. Zhang Yaodong Yu Jiantao Jiao Eric Xing L. Ghaoui Michael I. Jordan 96 2,525 0 24 Jan 2019
MMA Training: Direct Input Space Margin Maximization through Adversarial Training G. Ding Yash Sharma Kry Yik-Chau Lui Ruitong Huang AAML 51 272 0 06 Dec 2018
Disentangling Adversarial Robustness and Generalization David Stutz Matthias Hein Bernt Schiele AAML OOD 232 279 0 03 Dec 2018
Rademacher Complexity for Adversarially Robust Generalization Dong Yin Kannan Ramchandran Peter L. Bartlett AAML 69 258 0 29 Oct 2018
Motivating the Rules of the Game for Adversarial Example Research Justin Gilmer Ryan P. Adams Ian Goodfellow David G. Andersen George E. Dahl AAML 73 227 0 18 Jul 2018
Stochastic Gradient Descent on Separable Data: Exact Convergence with a Fixed Learning Rate Mor Shpigel Nacson Nathan Srebro Daniel Soudry FedML MLT 53 100 0 05 Jun 2018
Robustness May Be at Odds with Accuracy Dimitris Tsipras Shibani Santurkar Logan Engstrom Alexander Turner Aleksander Madry AAML 78 1,772 0 30 May 2018
Adversarially Robust Generalization Requires More Data Ludwig Schmidt Shibani Santurkar Dimitris Tsipras Kunal Talwar Aleksander Madry OOD AAML 116 786 0 30 Apr 2018
Towards Imperceptible and Robust Adversarial Example Attacks against Neural Networks Bo Luo Yannan Liu Lingxiao Wei Q. Xu AAML 37 142 0 15 Jan 2018
The Implicit Bias of Gradient Descent on Separable Data Daniel Soudry Elad Hoffer Mor Shpigel Nacson Suriya Gunasekar Nathan Srebro 71 908 0 27 Oct 2017
Towards Deep Learning Models Resistant to Adversarial Attacks Aleksander Madry Aleksandar Makelov Ludwig Schmidt Dimitris Tsipras Adrian Vladu SILM OOD 229 11,962 0 19 Jun 2017
Deep Residual Learning for Image Recognition Kaiming He Xinming Zhang Shaoqing Ren Jian Sun MedIm 1.4K 192,638 0 10 Dec 2015
DeepFool: a simple and accurate method to fool deep neural networks Seyed-Mohsen Moosavi-Dezfooli Alhussein Fawzi P. Frossard AAML 95 4,878 0 14 Nov 2015
Explaining and Harnessing Adversarial Examples Ian Goodfellow Jonathon Shlens Christian Szegedy AAML GAN 176 18,922 0 20 Dec 2014