Robustness via curvature regularization, and vice versa

Understand

State-of-the-art classifiers have been shown to be largely vulnerable to adversarial perturbations.

• One of the most effective strategies to improve robustness is adversarial training.
• In this paper, we investigate the effect of adversarial training on the geometry of the classification landscape and decision boundaries.
• We show in particular that adversarial training leads to a significant decrease in the curvature of the loss surface with respect to inputs, leading to a drastically more "linear" behaviour of the network.