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

AIにより推定されたラベル

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

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