PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defenses

arXiv:2310.13076v2 Announce Type: replace-cross
Abstract: State-of-the-art defenses against adversarial patch attacks can now achieve strong certifiable robustness with a marginal drop in model utility. However, this impressive performance typically comes at the cost of 10-100x more inference-time computation compared to undefended models -- the research community has witnessed an intense three-way trade-off between certifiable robustness, model utility, and computation efficiency. In this paper, we propose a defense framework named PatchCURE to approach this trade-off problem. PatchCURE provides sufficient "knobs" for …

adversarial art arxiv attacks can community computation cost cs.cr cs.cv defenses efficiency patch performance research robustness state utility