2 papers
cs.LG2025
Identifying and Understanding Cross-Class Features in Adversarial Training
Zeming Wei, Yiwen Guo, Yisen Wang
Adversarial training (AT) has been considered one of the most effective methods for making deep neural networks robust against adversarial attacks, while the training mechanisms an…
cs.LG2024
Adversarial Examples Are Not Real Features
Ang Li, Yifei Wang, Yiwen Guo +1
The existence of adversarial examples has been a mystery for years and attracted much interest. A well-known theory by \citet{ilyas2019adversarial} explains adversarial vulnerabili…