Narrowing Class-Wise Robustness Gaps in Adversarial Training

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Amerehi, Fatemeh, Healy, Patrick
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912284145614848
author Amerehi, Fatemeh
Healy, Patrick
author_facet Amerehi, Fatemeh
Healy, Patrick
contents 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 shifts caused by adversarial examples. While this method can improve robustness, it may also hinder generalization to clean examples and exacerbate performance imbalances across different classes. This paper explores the impact of adversarial training on both overall and class-specific performance, as well as its spill-over effects. We observe that enhanced labeling during training boosts adversarial robustness by 53.50% and mitigates class imbalances by 5.73%, leading to improved accuracy in both clean and adversarial settings compared to standard adversarial training.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16179
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Narrowing Class-Wise Robustness Gaps in Adversarial Training
Amerehi, Fatemeh
Healy, Patrick
Computer Vision and Pattern Recognition
Machine Learning
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 shifts caused by adversarial examples. While this method can improve robustness, it may also hinder generalization to clean examples and exacerbate performance imbalances across different classes. This paper explores the impact of adversarial training on both overall and class-specific performance, as well as its spill-over effects. We observe that enhanced labeling during training boosts adversarial robustness by 53.50% and mitigates class imbalances by 5.73%, leading to improved accuracy in both clean and adversarial settings compared to standard adversarial training.
title Narrowing Class-Wise Robustness Gaps in Adversarial Training
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2503.16179