Raising the Bar for Certified Adversarial Robustness with Diffusion Models. (arXiv:2305.10388v1 [cs.LG])

Certified defenses against adversarial attacks offer formal guarantees on the
robustness of a model, making them more reliable than empirical methods such as
adversarial training, whose effectiveness is often later reduced by unseen
attacks. Still, the limited certified robustness that is currently achievable
has been a bottleneck for their practical adoption. Gowal et al. and Wang et
al. have shown that generating additional training data using state-of-the-art
diffusion models can considerably improve the robustness of adversarial
training. In this work, …

adversarial adversarial attacks attacks certified diffusion models making offer robustness training