53 citations · 55 across the 2 of their papers we have counts for
2 papers
cs.LG2023★ 2 cited
Generalization Bounds for Adversarial Contrastive Learning
Xin Zou, Weiwei Liu
Deep networks are well-known to be fragile to adversarial attacks, and adversarial training is one of the most popular methods used to train a robust model. To take advantage of un…
cs.CV2023★ 53 cited
Better Diffusion Models Further Improve Adversarial Training
Zekai Wang, Tianyu Pang, Chao Du +3
It has been recognized that the data generated by the denoising diffusion probabilistic model (DDPM) improves adversarial training. After two years of rapid development in diffusio…