MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples

Nicholas Carlini; David Wagner

MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples

Machine Learning 2017-11-27 v1 Artificial Intelligence Cryptography and Security

Authors: Nicholas Carlini , David Wagner

Abstract

MagNet and "Efficient Defenses..." were recently proposed as a defense to adversarial examples. We find that we can construct adversarial examples that defeat these defenses with only a slight increase in distortion.

MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples

Abstract

Keywords

Cite

Related papers