BriefGPT.xyz
Apr, 2018
CVPR 2018白盒子对抗攻击防御方法的鲁棒性研究
On the Robustness of the CVPR 2018 White-Box Adversarial Example Defenses
HTML
PDF
Anish Athalye, Nicholas Carlini
TL;DR
本研究针对2018 CVPR中提出的两种白盒防御策略进行评估，发现它们并不有效，通过现有技术可以将被防御的神经网络模型的准确率降至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
→