Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training

Jiacheng Zhang; Feng Liu; Dawei Zhou; Jingfeng ZHANG; Tongliang Liu

2024 ICML ICML 2024

Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Jiacheng Zhang, Feng Liu, Dawei Zhou, Jingfeng ZHANG, Tongliang Liu

Topics

Machine Learning > Core Methods > Classification Machine Learning > Optimization & Theory > Learning Theory Deep Learning > Techniques > Model Architecture

Keywords

robustness adversarial training class activation mapping perturbation budget accuracy pixel reweighting

Download PDF