Understanding Adversarial Robustness Through Loss Landscape Geometries

no code implementations • 22 Jul 2019 • Vinay Uday Prabhu, Dian Ang Yap, Joyce Xu, John Whaley

In this paper, we harness the state-of-the-art "filter normalization" technique of loss-surface visualization to qualitatively understand the consequences of using adversarial training data augmentation as the explicit regularization technique of choice.

Adversarial Robustness Data Augmentation