论文标题
通过异常检测来识别音频对抗示例
Identifying Audio Adversarial Examples via Anomalous Pattern Detection
论文作者
论文摘要
基于深神经网络的音频处理模型即使在对抗性音频波形的99.9％类似于良性样本时，也容易受到对抗性攻击的影响。鉴于基于DNN的音频识别系统的广泛应用，检测对抗性示例的存在具有很高的实际相关性。通过在这些模型的激活空间中应用异常的模式检测技术，我们表明，对音频处理系统的最新和当前最新的对抗性攻击中有2个系统系统地导致节点的某些子集中的激活高于预期的激活，并且我们可以检测到这些因素，最高为0.98，在BENIGNINGSPALES上没有达到0.98的auc，却没有降级。
Audio processing models based on deep neural networks are susceptible to adversarial attacks even when the adversarial audio waveform is 99.9% similar 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.
