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

Authors: Anish Athalye, Nicholas Carlini
Published: 2018-04-10

Source: https://arxiv.org/abs/1804.03286

PDF: https://arxiv.org/pdf/1804.03286

Labels Predicted by AI

モデルの頑健性保証 透かし 敵対的攻撃

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

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