## A Closer Look at the Adversarial Robustness of Information Bottleneck Models

18 Jun 2021, 13:23 (modified: 23 Jun 2021, 19:04)ICML 2021 Workshop AML PosterReaders: Everyone
Abstract: We study the adversarial robustness of information bottleneck models for classification. Previous works showed that the robustness of models trained with information bottlenecks can improve upon adversarial training. Our evaluation under a diverse range of white-box $l_{\infty}$ attacks suggests that information bottlenecks alone are not a strong defense strategy, and that previous results were likely influenced by gradient obfuscation.