Timezone: »

 
A Closer Look at the Adversarial Robustness of Information Bottleneck Models
Iryna Korshunova · David Stutz · Alexander Alemi · Olivia Wiles · Sven Gowal
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.

Author Information

Iryna Korshunova (Ghent University)
David Stutz (Max Planck Institute for Informatics)
Alexander Alemi (Google)
Olivia Wiles (DeepMind)
Sven Gowal (DeepMind)

More from the Same Authors