English

A Closer Look at the Adversarial Robustness of Information Bottleneck Models

Machine Learning 2021-07-14 v1

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 ll_{\infty} attacks suggests that information bottlenecks alone are not a strong defense strategy, and that previous results were likely influenced by gradient obfuscation.

Keywords

Cite

@article{arxiv.2107.05712,
  title  = {A Closer Look at the Adversarial Robustness of Information Bottleneck Models},
  author = {Iryna Korshunova and David Stutz and Alexander A. Alemi and Olivia Wiles and Sven Gowal},
  journal= {arXiv preprint arXiv:2107.05712},
  year   = {2021}
}