On the Robustness of the CVPR 2018 White-Box Adversarial Example Defenses
Anish Athalye, Nicholas Carlini · arXiv (Cornell University) · 2018
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%.