Adversarial Training Can Hurt Generalization

14 June 2019

Papers citing "Adversarial Training Can Hurt Generalization"

50 / 66 papers shown

Title
Adversarially Pretrained Transformers may be Universally Robust In-Context Learners Soichiro Kumano Hiroshi Kera Toshihiko Yamasaki AAML 16 0 0 20 May 2025
Adversarial Training for Multimodal Large Language Models against Jailbreak Attacks Liming Lu Shuchao Pang Siyuan Liang Haotian Zhu Xiyu Zeng Aishan Liu Yunhuai Liu Yongbin Zhou AAML 53 2 0 05 Mar 2025
FAIR-TAT: Improving Model Fairness Using Targeted Adversarial Training Tejaswini Medi Steffen Jung M. Keuper AAML 44 3 0 30 Oct 2024
$H$ -Consistency Guarantees for Regression Anqi Mao M. Mohri Yutao Zhong 36 9 0 28 Mar 2024
Theoretical Understanding of Learning from Adversarial Perturbations Soichiro Kumano Hiroshi Kera Toshihiko Yamasaki AAML 51 1 0 16 Feb 2024
Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective Yue Xing Xiaofeng Lin Qifan Song Yi Tian Xu Belinda Zeng Guang Cheng SSL 31 0 0 26 Jan 2024
Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Training Shruthi Gowda Bahram Zonooz Elahe Arani AAML 36 2 0 26 Jan 2024
MIMIR: Masked Image Modeling for Mutual Information-based Adversarial Robustness Xiaoyun Xu Shujian Yu Jingzheng Wu S. Picek AAML 35 0 0 08 Dec 2023
Input margins can predict generalization too Coenraad Mouton Marthinus W. Theunissen Marelie Hattingh Davel AAML UQCV AI4CE 23 3 0 29 Aug 2023
Collaborative Development of NLP models Fereshte Khani Marco Tulio Ribeiro 38 2 0 20 May 2023
Optimization and Optimizers for Adversarial Robustness Hengyue Liang Buyun Liang Le Peng Ying Cui Tim Mitchell Ju Sun AAML 28 5 0 23 Mar 2023
Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels Simone Bombari Shayan Kiyani Marco Mondelli AAML 48 10 0 03 Feb 2023
Learning Against Distributional Uncertainty: On the Trade-off Between Robustness and Specificity Shixiong Wang Haowei Wang Xinke Li Jean Honorio OOD 65 1 0 31 Jan 2023
A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability Chengtai Cao Fan Zhou Yurou Dai Jianping Wang Kunpeng Zhang AAML 31 28 0 21 Dec 2022
Learning Antidote Data to Individual Unfairness Peizhao Li Ethan Xia Hongfu Liu FedML FaML 24 9 0 29 Nov 2022
Adversarial Rademacher Complexity of Deep Neural Networks Jiancong Xiao Yanbo Fan Ruoyu Sun Zhimin Luo AAML 22 22 0 27 Nov 2022
Augmentation with Projection: Towards an Effective and Efficient Data Augmentation Paradigm for Distillation Ziqi Wang Yuexin Wu Frederick Liu Daogao Liu Le Hou Hongkun Yu Jing Li Heng Ji 45 5 0 21 Oct 2022
Stability Analysis and Generalization Bounds of Adversarial Training Jiancong Xiao Yanbo Fan Ruoyu Sun Jue Wang Zhimin Luo AAML 38 30 0 03 Oct 2022
Adaptive Smoothness-weighted Adversarial Training for Multiple Perturbations with Its Stability Analysis Jiancong Xiao Zeyu Qin Yanbo Fan Baoyuan Wu Jue Wang Zhimin Luo AAML 39 7 0 02 Oct 2022
MaskTune: Mitigating Spurious Correlations by Forcing to Explore Saeid Asgari Taghanaki Aliasghar Khani Fereshte Khani A. Gholami Linh-Tam Tran Ali Mahdavi-Amiri Ghassan Hamarneh AAML 46 45 0 30 Sep 2022
Annealing Optimization for Progressive Learning with Stochastic Approximation Christos N. Mavridis John S. Baras 28 10 0 06 Sep 2022
Aug-NeRF: Training Stronger Neural Radiance Fields with Triple-Level Physically-Grounded Augmentations Tianlong Chen Peihao Wang Zhiwen Fan Zhangyang Wang 38 55 0 04 Jul 2022
On the Role of Generalization in Transferability of Adversarial Examples Yilin Wang Farzan Farnia AAML 24 10 0 18 Jun 2022
Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power Binghui Li Jikai Jin Han Zhong J. Hopcroft Liwei Wang OOD 87 27 0 27 May 2022
Learn2Weight: Parameter Adaptation against Similar-domain Adversarial Attacks Siddhartha Datta AAML 38 4 0 15 May 2022
Fast AdvProp Jieru Mei Yucheng Han Yutong Bai Yixiao Zhang Yingwei Li Xianhang Li Alan Yuille Cihang Xie AAML 29 8 0 21 Apr 2022
Revisiting the Adversarial Robustness-Accuracy Tradeoff in Robot Learning Mathias Lechner Alexander Amini Daniela Rus T. Henzinger AAML 34 10 0 15 Apr 2022
Robust and Accurate -- Compositional Architectures for Randomized Smoothing Miklós Z. Horváth Mark Niklas Muller Marc Fischer Martin Vechev UQCV AAML 10 13 0 01 Apr 2022
Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse Martin Pawelczyk Teresa Datta Johannes van-den-Heuvel Gjergji Kasneci Himabindu Lakkaraju 24 38 0 13 Mar 2022
Sparsity Winning Twice: Better Robust Generalization from More Efficient Training Tianlong Chen Zhenyu Zhang Pengju Wang Santosh Balachandra Haoyu Ma Zehao Wang Zhangyang Wang OOD AAML 100 47 0 20 Feb 2022
A Theory of PAC Learnability under Transformation Invariances Hang Shao Omar Montasser Avrim Blum 27 18 0 15 Feb 2022
Efficient and Robust Classification for Sparse Attacks M. Beliaev Payam Delgosha Hamed Hassani Ramtin Pedarsani AAML 27 2 0 23 Jan 2022
CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networks Hao Xue Kaixiong Zhou Tianlong Chen Kai Guo Xia Hu Yi Chang Xin Wang AAML 32 15 0 28 Oct 2021
Trustworthy AI: From Principles to Practices Bo-wen Li Peng Qi Bo Liu Shuai Di Jingen Liu Jiquan Pei Jinfeng Yi Bowen Zhou 119 357 0 04 Oct 2021
Distributionally Robust Learning Ruidi Chen I. Paschalidis OOD 32 65 0 20 Aug 2021
Advances in adversarial attacks and defenses in computer vision: A survey Naveed Akhtar Ajmal Mian Navid Kardan M. Shah AAML 41 236 0 01 Aug 2021
Analysis and Applications of Class-wise Robustness in Adversarial Training Qi Tian Kun Kuang Ke Jiang Fei Wu Yisen Wang AAML 20 46 0 29 May 2021
Improved OOD Generalization via Adversarial Training and Pre-training Mingyang Yi Lu Hou Jiacheng Sun Lifeng Shang Xin Jiang Qun Liu Zhi-Ming Ma VLM 33 83 0 24 May 2021
Relating Adversarially Robust Generalization to Flat Minima David Stutz Matthias Hein Bernt Schiele OOD 41 65 0 09 Apr 2021
Neural Network Robustness as a Verification Property: A Principled Case Study Marco Casadio Ekaterina Komendantskaya M. Daggitt Wen Kokke Guy Katz Guy Amir Idan Refaeli OOD AAML 21 39 0 03 Apr 2021
Reweighting Augmented Samples by Minimizing the Maximal Expected Loss Mingyang Yi Lu Hou Lifeng Shang Xin Jiang Qun Liu Zhi-Ming Ma 12 19 0 16 Mar 2021
Adversarial Training is Not Ready for Robot Learning Mathias Lechner Ramin Hasani Radu Grosu Daniela Rus T. Henzinger AAML 38 34 0 15 Mar 2021
A Robust Adversarial Network-Based End-to-End Communications System With Strong Generalization Ability Against Adversarial Attacks Yudi Dong Huaxia Wang Yu-dong Yao AAML GAN 24 5 0 03 Mar 2021
Training a Resilient Q-Network against Observational Interference Chao-Han Huck Yang I-Te Danny Hung Ouyang Yi Pin-Yu Chen OOD 31 14 0 18 Feb 2021
Online Deterministic Annealing for Classification and Clustering Christos N. Mavridis John S. Baras ODL 27 17 0 11 Feb 2021
Recent Advances in Adversarial Training for Adversarial Robustness Tao Bai Jinqi Luo Jun Zhao Bihan Wen Qian Wang AAML 86 476 0 02 Feb 2021
Fundamental Tradeoffs in Distributionally Adversarial Training M. Mehrabi Adel Javanmard Ryan A. Rossi Anup B. Rao Tung Mai AAML 20 18 0 15 Jan 2021
Precise Statistical Analysis of Classification Accuracies for Adversarial Training Adel Javanmard Mahdi Soltanolkotabi AAML 33 61 0 21 Oct 2020
Viewmaker Networks: Learning Views for Unsupervised Representation Learning Alex Tamkin Mike Wu Noah D. Goodman SSL 32 64 0 14 Oct 2020
A law of robustness for two-layers neural networks Sébastien Bubeck Yuanzhi Li Dheeraj M. Nagaraj 35 57 0 30 Sep 2020