Causal Information Bottleneck Boosts Adversarial Robustness of Deep Neural Network

Understand

The information bottleneck (IB) method is a feasible defense solution against adversarial attacks in deep learning.

• However, this method suffers from the spurious correlation, which leads to the limitation of its further improvement of adversarial robustness.
• In this paper, we incorporate the causal inference into the IB framework to alleviate such a problem.
• Specifically, we divide the features obtained by the IB method into robust features (content information) and non-robust features (style information) via the instrumental variables to estimate the causal effects.