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

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.

References in corpus (1)

• APE-GAN: Adversarial Perturbation Elimination with GAN

Cited by in corpus (3)

• Enhancing Gradient-based Attacks with Symbolic Intervals
• Bandlimiting Neural Networks Against Adversarial Attacks
• A Computationally Efficient Method for Defending Adversarial Deep Learning Attacks