2 papers
cs.LG2025
On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics
Binghui Li, Yuanzhi Li
Similar to surprising performance in the standard deep learning, deep nets trained by adversarial training also generalize well for unseen clean data (natural data). However, despi…
cs.LG2025
Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data
Binghui Li, Yuanzhi Li
Adversarial training is a widely-applied approach to training deep neural networks to be robust against adversarial perturbation. However, although adversarial training has achieve…