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

Code

• github.com/carlini/breaking_efficient_defenses
  OfficialIn papertf★ 0

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.

Reproductions