New CleverHans Feature: Better Adversarial Robustness Evaluations with Attack Bundling

arXiv: Cryptography and Security, Volume abs/1811.03685, 2018.

Cited by: 0|Bibtex|Views91
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

This technical report describes a new feature of the CleverHans library called bundling. Many papers about adversarial examples present lists of error rates corresponding to different attack algorithms. A common approach is to take the maximum across this list and compare defenses against that error rate. We argue that a better approach ...More

Code:

Data:

Your rating :
0

 

Tags
Comments