arXiv:1705.07263cs.LG
Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods
Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.
Abstract
Neural networks are known to be vulnerable to adversarial examples: inputs that are close to natural inputs but classified incorrectly. In order to better understand the space of adversarial examples, we survey ten recent proposals that are designed for detection and compare their efficacy. We show that all can be defeated by constructing new loss functions. We conclude that adversarial examples are significantly harder to detect than previously appreciated, and the properties believed to be intrinsic to adversarial examples are in fact not. Finally, we propose several simple guidelines for evaluating future proposed defenses.
I agree - it's a surprising and cool paper. There has been some work done on fooling network ensembles by constructing constructing a Bayesian posterior over weights using dropout [0]. This is an ensemble of weights for the same network, not over different architectures…
tMcGrathView on HNParent context