← Search

A. Adam Ding

2 accepted papers

2022

Finding Dynamics Preserving Adversarial Winning Tickets

AISTATS 2022poster

Modern deep neural networks (DNNs) are vulnerable to adversarial attacks and adversarial training has been shown to be a promising method for improving the adversarial robustness of DNNs. Pruning methods have been considered in adversarial context to reduce model capacity and improve adversarial rob…