Identifying Audio Adversarial Examples via Anomalous Pattern Detection

Authors: Victor Akinwande, Celia Cintas, Skyler Speakman, Srihari Sridharan
Published: 2020-02-13 | Updated: 2020-07-25

Source: https://arxiv.org/abs/2002.05463

PDF: https://arxiv.org/pdf/2002.05463

Labels Predicted by AI

敵対的攻撃手法 敵対的サンプルの脆弱性 機械学習の応用

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

Audio processing models based on deep neural networks are susceptible to adversarial attacks even when the adversarial audio waveform is 99.9 to a benign sample. Given the wide application of DNN-based audio recognition systems, detecting the presence of adversarial examples is of high practical relevance. By applying anomalous pattern detection techniques in the activation space of these models, we show that 2 of the recent and current state-of-the-art adversarial attacks on audio processing systems systematically lead to higher-than-expected activation at some subset of nodes and we can detect these with up to an AUC of 0.98 with no degradation in performance on benign samples.