[ICLR 2022] "Sparsity Winning Twice: Better Robust Generalization from More Efficient Training" by Tianlong Chen*, Zhenyu Zhang*, Pengjun Wang*, Santosh Balachandra*, Haoyu Ma*, Zehao Wang, Zhangyang Wang

data augmentation alone can improve adversarial training

Combating robust overfitting in adversarial training via AdvLC

Code for the paper "Interpolation can hurt robust generalization even when there is no noise" available here: https://papers.nips.cc/paper/2021/hash/c4f2c88e16a579900657c18726641c81-Abstract.html

[ICML 2026] Official implementation of "Toward Understanding Adversarial Distillation: Why Robust Teachers Fail."