Search Results for author: Kaijie Cai

Found 1 papers, 0 papers with code

PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patch

no code implementations5 Jul 2022 Ke Xu, Yao Xiao, Zhaoheng Zheng, Kaijie Cai, Ram Nevatia

Despite the diversity in attack patterns, adversarial patches tend to be highly textured and different in appearance from natural images.

Image Classification object-detection +3

Cannot find the paper you are looking for? You can Submit a new open access paper.