pith. sign in

arxiv: 1706.04701 · v1 · pith:MEV3SIFJnew · submitted 2017-06-15 · 💻 cs.LG

Adversarial Example Defenses: Ensembles of Weak Defenses are not Strong

classification 💻 cs.LG
keywords defensesadversarialdefenseexamplesstrongweakcomponentsproposed
0
0 comments X
read the original abstract

Ongoing research has proposed several methods to defend neural networks against adversarial examples, many of which researchers have shown to be ineffective. We ask whether a strong defense can be created by combining multiple (possibly weak) defenses. To answer this question, we study three defenses that follow this approach. Two of these are recently proposed defenses that intentionally combine components designed to work well together. A third defense combines three independent defenses. For all the components of these defenses and the combined defenses themselves, we show that an adaptive adversary can create adversarial examples successfully with low distortion. Thus, our work implies that ensemble of weak defenses is not sufficient to provide strong defense against adversarial examples.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.