Understanding and Mitigating the Tradeoff Between Robustness and Accuracy

25 February 2020

Papers citing "Understanding and Mitigating the Tradeoff Between Robustness and Accuracy"

50 / 149 papers shown

Title
Reliable learning in challenging environments Maria-Florina Balcan Steve Hanneke Rattana Pukdee Dravyansh Sharma OOD 30 4 0 06 Apr 2023
Generalist: Decoupling Natural and Robust Generalization Hongjun Wang Yisen Wang OOD AAML 49 14 0 24 Mar 2023
Randomized Adversarial Training via Taylor Expansion Gao Jin Xinping Yi Dengyu Wu Ronghui Mu Xiaowei Huang AAML 44 34 0 19 Mar 2023
Among Us: Adversarially Robust Collaborative Perception by Consensus Yiming Li Qi Fang Jiamu Bai Siheng Chen Felix Juefei Xu Chen Feng AAML 34 27 0 16 Mar 2023
Beyond Pretrained Features: Noisy Image Modeling Provides Adversarial Defense Zunzhi You Daochang Liu Bohyung Han Chang Xu AAML VLM 52 4 0 02 Feb 2023
Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothing Yatong Bai Brendon G. Anderson Aerin Kim Somayeh Sojoudi AAML 33 18 0 29 Jan 2023
Denoising Diffusion Probabilistic Models as a Defense against Adversarial Attacks Lars Lien Ankile Anna Midgley Sebastian Weisshaar DiffM 21 5 0 17 Jan 2023
Provable Robust Saliency-based Explanations Chao Chen Chenghua Guo Guixiang Ma Ming Zeng Xi Zhang Sihong Xie AAML FAtt 36 0 0 28 Dec 2022
Advancing Deep Metric Learning Through Multiple Batch Norms And Multi-Targeted Adversarial Examples Inderjeet Singh Kazuya Kakizaki Toshinori Araki AAML OOD 29 0 0 29 Nov 2022
Understanding the Impact of Adversarial Robustness on Accuracy Disparity Yuzheng Hu Fan Wu Hongyang R. Zhang Hang Zhao 34 8 0 28 Nov 2022
Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack Yunfeng Diao He-Nan Wang Tianjia Shao Yong-Liang Yang Kun Zhou David C. Hogg Meng Wang AAML 40 6 0 21 Nov 2022
Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Games Maria-Florina Balcan Rattana Pukdee Pradeep Ravikumar Hongyang R. Zhang AAML 33 12 0 23 Oct 2022
Evolution of Neural Tangent Kernels under Benign and Adversarial Training Noel Loo Ramin Hasani Alexander Amini Daniela Rus AAML 34 13 0 21 Oct 2022
A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities Andrea Tocchetti Lorenzo Corti Agathe Balayn Mireia Yurrita Philip Lippmann Marco Brambilla Jie-jin Yang 27 10 0 17 Oct 2022
Strength-Adaptive Adversarial Training Chaojian Yu Dawei Zhou Li Shen Jun Yu Bo Han Biwei Huang Nannan Wang Tongliang Liu OOD 17 2 0 04 Oct 2022
Enhance the Visual Representation via Discrete Adversarial Training Xiaofeng Mao YueFeng Chen Ranjie Duan Yao Zhu Gege Qi Shaokai Ye Xiaodan Li Rong Zhang Hui Xue 44 31 0 16 Sep 2022
Sound and Complete Verification of Polynomial Networks Elias Abad Rocamora Mehmet Fatih Şahin Fanghui Liu Grigorios G. Chrysos V. Cevher 23 5 0 15 Sep 2022
ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets Damien Teney Yong Lin Seong Joon Oh Ehsan Abbasnejad OOD 386 47 0 01 Sep 2022
Data Isotopes for Data Provenance in DNNs Emily Wenger Xiuyu Li Ben Y. Zhao Vitaly Shmatikov 20 12 0 29 Aug 2022
Lower Difficulty and Better Robustness: A Bregman Divergence Perspective for Adversarial Training Zihui Wu Haichang Gao Bingqian Zhou Xiaoyan Guo Shudong Zhang AAML 30 0 0 26 Aug 2022
Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift Ananya Kumar Tengyu Ma Percy Liang Aditi Raghunathan UQCV OODD OOD 42 38 0 18 Jul 2022
Counterbalancing Teacher: Regularizing Batch Normalized Models for Robustness Saeid Asgari Taghanaki A. Gholami Fereshte Khani Kristy Choi Linh-Tam Tran Ran Zhang Aliasghar Khani 11 0 0 04 Jul 2022
Utilizing Class Separation Distance for the Evaluation of Corruption Robustness of Machine Learning Classifiers George J. Siedel S. Vock Andrey Morozov Stefan Voss 11 3 0 27 Jun 2022
Wavelet Regularization Benefits Adversarial Training Jun Yan Huilin Yin Xiaoyang Deng Zi-qin Zhao Wancheng Ge Hao Zhang Gerhard Rigoll AAML 19 2 0 08 Jun 2022
Adversarial Unlearning: Reducing Confidence Along Adversarial Directions Amrith Rajagopal Setlur Benjamin Eysenbach Virginia Smith Sergey Levine 14 18 0 03 Jun 2022
Semi-supervised Semantics-guided Adversarial Training for Trajectory Prediction Ruochen Jiao Xiangguo Liu Takami Sato Qi Alfred Chen Qi Zhu AAML 40 20 0 27 May 2022
Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification Leo Schwinn Leon Bungert A. Nguyen René Raab Falk Pulsmeyer Doina Precup Björn Eskofier Dario Zanca OOD 56 12 0 19 May 2022
EllSeg-Gen, towards Domain Generalization for head-mounted eyetracking Rakshit Kothari Reynold J. Bailey Christopher Kanan J. Pelz Gabriel J. Diaz OOD 12 10 0 04 May 2022
MIRST-DM: Multi-Instance RST with Drop-Max Layer for Robust Classification of Breast Cancer Shoukun Sun Min Xian Aleksandar Vakanski Hossny Ghanem OOD 11 3 0 02 May 2022
Adversarial Fine-tune with Dynamically Regulated Adversary Peng-Fei Hou Ming Zhou Jie Han Petr Musílek Xingyu Li AAML 23 3 0 28 Apr 2022
The Effects of Regularization and Data Augmentation are Class Dependent Randall Balestriero Léon Bottou Yann LeCun 33 94 0 07 Apr 2022
Improving Vision Transformers by Revisiting High-frequency Components Jiawang Bai Liuliang Yuan Shutao Xia Shuicheng Yan Zhifeng Li Wei Liu ViT 16 90 0 03 Apr 2022
A Manifold View of Adversarial Risk Wen-jun Zhang Yikai Zhang Xiaoling Hu Mayank Goswami Chao Chen Dimitris N. Metaxas AAML 19 6 0 24 Mar 2022
Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness Tejas Gokhale Swaroop Mishra Man Luo Bhavdeep Singh Sachdeva Chitta Baral 52 29 0 15 Mar 2022
Defending Black-box Skeleton-based Human Activity Classifiers He-Nan Wang Yunfeng Diao Zichang Tan G. Guo AAML 51 10 0 09 Mar 2022
Why adversarial training can hurt robust accuracy Jacob Clarysse Julia Hörrmann Fanny Yang AAML 13 18 0 03 Mar 2022
Ensemble Methods for Robust Support Vector Machines using Integer Programming Jannis Kurtz 11 0 0 03 Mar 2022
Robustness and Accuracy Could Be Reconcilable by (Proper) Definition Tianyu Pang Min-Bin Lin Xiao Yang Junyi Zhu Shuicheng Yan 30 119 0 21 Feb 2022
Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution Ananya Kumar Aditi Raghunathan Robbie Jones Tengyu Ma Percy Liang OODD 44 640 0 21 Feb 2022
Learning Representations Robust to Group Shifts and Adversarial Examples Ming-Chang Chiu Xuezhe Ma OOD 11 0 0 18 Feb 2022
Can Adversarial Training Be Manipulated By Non-Robust Features? Lue Tao Lei Feng Hongxin Wei Jinfeng Yi Sheng-Jun Huang Songcan Chen AAML 81 16 0 31 Jan 2022
How does unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis Shuai Zhang Hao Wu Sijia Liu Pin-Yu Chen Jinjun Xiong SSL MLT 41 22 0 21 Jan 2022
Benign Overfitting in Adversarially Robust Linear Classification Jinghui Chen Yuan Cao Quanquan Gu AAML SILM 34 10 0 31 Dec 2021
PRIME: A few primitives can boost robustness to common corruptions Apostolos Modas Rahul Rade Guillermo Ortiz-Jiménez Seyed-Mohsen Moosavi-Dezfooli P. Frossard AAML 25 41 0 27 Dec 2021
Interpolated Joint Space Adversarial Training for Robust and Generalizable Defenses Chun Pong Lau Jiang-Long Liu Hossein Souri Wei-An Lin S. Feizi Ramalingam Chellappa AAML 29 12 0 12 Dec 2021
Pyramid Adversarial Training Improves ViT Performance Charles Herrmann Kyle Sargent Lu Jiang Ramin Zabih Huiwen Chang Ce Liu Dilip Krishnan Deqing Sun ViT 29 56 0 30 Nov 2021
Pareto Adversarial Robustness: Balancing Spatial Robustness and Sensitivity-based Robustness Ke Sun Mingjie Li Zhouchen Lin AAML 24 2 0 03 Nov 2021
Adversarial Robustness with Semi-Infinite Constrained Learning Alexander Robey Luiz F. O. Chamon George J. Pappas Hamed Hassani Alejandro Ribeiro AAML OOD 118 42 0 29 Oct 2021
Distinguishing rule- and exemplar-based generalization in learning systems Ishita Dasgupta Erin Grant Thomas L. Griffiths 12 13 0 08 Oct 2021
Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks Hanxun Huang Yisen Wang S. Erfani Quanquan Gu James Bailey Xingjun Ma AAML TPM 46 100 0 07 Oct 2021