On the Robustness of the CVPR 2018 White-Box Adversarial Example Defenses

Code

• github.com/anishathalye/Guided-Denoise
  OfficialIn papertf★ 0
• github.com/anishathalye/pixel-deflection
  tf★ 0

Abstract

Neural networks are known to be vulnerable to adversarial examples. In this note, we evaluate the two white-box defenses that appeared at CVPR 2018 and find they are ineffective: when applying existing techniques, we can reduce the accuracy of the defended models to 0%.

Reproductions