New CleverHans Feature: Better Adversarial Robustness Evaluations with Attack Bundling
arXiv: Cryptography and Security, Volume abs/1811.03685, 2018.
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
Full Text (Upload PDF)
PPT (Upload PPT)