Erratum Concerning the Obfuscated Gradients Attack on Stochastic Activation Pruning

Authors: Guneet S. Dhillon, Nicholas Carlini
Published: 2020-09-30

Source: https://arxiv.org/abs/2010.00071

PDF: https://arxiv.org/pdf/2010.00071

Labels Predicted by AI

ロバスト性向上手法 ウォーターマーキング 攻撃の評価

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

Stochastic Activation Pruning (SAP) (Dhillon et al., 2018) is a defense to adversarial examples that was attacked and found to be broken by the “Obfuscated Gradients” paper (Athalye et al., 2018). We discover a flaw in the re-implementation that artificially weakens SAP. When SAP is applied properly, the proposed attack is not effective. However, we show that a new use of the BPDA attack technique can still reduce the accuracy of SAP to 0.1