Skip to yearly menu bar Skip to main content

Workshop: A Blessing in Disguise: The Prospects and Perils of Adversarial Machine Learning

A Closer Look at the Adversarial Robustness of Information Bottleneck Models

Iryna Korshunova · David Stutz · Alexander Alemi · Olivia Wiles · Sven Gowal

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.

Chat is not available.