paper-with-me

홈 › Papers

WAT: Improve the Worst-class Robustness in Adversarial Training

2023-02-08 · Boqi Li, Weiwei Liu

Deep Neural Networks (DNN) have been shown to be vulnerable to adversarial examples. Adversarial training (AT) is a popular and effective strategy to defend against adversarial attacks. Recent works (Benz et al., 2020; Xu et al., 2021; Tian et al., 2021) have shown that a robust model well-trained by AT exhibits a remarkable robustness disparity among classes, and propose various methods to obtain consistent robust accuracy across classes. Unfortunately, these methods sacrifice a good deal of the average robust accuracy. Accordingly, this paper proposes a novel framework of worst-class adversarial training and leverages no-regret dynamics to solve this problem. Our goal is to obtain a classifier with great performance on worst-class and sacrifice just a little average robust accuracy at the same time. We then rigorously analyze the theoretical properties of our proposed algorithm, and the generalization error bound in terms of the worst-class robust risk. Furthermore, we propose a measurement to evaluate the proposed method in terms of both the average and worst-class accuracies. Experiments on various datasets and networks show that our proposed method outperforms the state-of-the-art approaches.

📄 PDF Abstract BibTeX arXiv:2302.04025

Code (1)

boqili/wat 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Narrowing Class-Wise Robustness Gaps in Adversarial Training

2025-03-20 · Fatemeh Amerehi, Patrick Healy

Efforts to address declining accuracy as a result of data shifts often involve various data-augmentation strategies. Adversarial training is one such method, designed to improve robustness to worst-case distribution shif…

Adversarial RobustnessClass-Specific PerformanceData Augmentation

Improved robustness to adversarial examples using Lipschitz regularization of the loss

2018-10-01 · ICLR 2019 5 · Chris Finlay, Adam Oberman, Bilal Abbasi

We augment adversarial training (AT) with worst case adversarial training (WCAT) which improves adversarial robustness by 11% over the current state-of-the-art result in the $\ell_2$ norm on CIFAR-10. We obtain verifiabl…

Adversarial Robustness

DAFA: Distance-Aware Fair Adversarial Training

2024-01-23 · Hyungyu Lee, Saehyung Lee, Hyemi Jang, Junsung Park 외

The disparity in accuracy between classes in standard training is amplified during adversarial training, a phenomenon termed the robust fairness problem. Existing methodologies aimed to enhance robust fairness by sacrifi…

Fairness

Principal Eigenvalue Regularization for Improved Worst-Class Certified Robustness of Smoothed Classifiers

2025-03-21 · Gaojie Jin, Tianjin Huang, Ronghui Mu, Xiaowei Huang

Recent studies have identified a critical challenge in deep neural networks (DNNs) known as ``robust fairness", where models exhibit significant disparities in robust accuracy across different classes. While prior work h…

Adversarial RobustnessFairness

Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization

2020-02-26 · ICML 2020 1 · Sicheng Zhu, Xiao Zhang, David Evans

Training machine learning models that are robust against adversarial inputs poses seemingly insurmountable challenges. To better understand adversarial robustness, we consider the underlying problem of learning robust re…

Adversarial Robustness