Robustness via curvature regularization, and vice versa

CVPR, Volume abs/1811.09716, 2019.

Cited by: 63|Bibtex|Views18
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

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 particu...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments