Synthetic speech detection is one of the most important research problems in audio security. Meanwhile, deep neural networks are vulnerable to adversarial attacks. Therefore, we establish a comprehensive benchmark to evaluate the transferability of adversarial attacks on the synthetic speech detection task. Specifically, we attempt to investigate: 1) The transferability of adversarial attacks between different features. 2) The influence of varying extraction hyperparameters of features on the transferability of adversarial attacks. 3) The effect of clipping or self-padding operation on the transferability of adversarial attacks. By performing these analyses, we summarise the weaknesses of synthetic speech detectors and the transferability behaviours of adversarial attacks, which provide insights for future research. More details can be found at https://gitee.com/djc_QRICK/Attack-Transferability-On-Synthetic-Detection.
翻译:合成语音探测是音频安全方面最重要的研究问题之一。与此同时,深神经网络很容易受到对抗性攻击。因此,我们建立了一个综合基准,以评价合成语音探测任务对抗性攻击的可转移性。具体地说,我们试图调查:(1) 对抗性攻击在不同特征之间的可转移性。(2) 不同提取性特征对对抗性攻击可转移性的影响。(3) 剪裁或自制操作对对抗性攻击可转移性的影响。通过进行这些分析,我们总结合成语音探测器的弱点和对抗性攻击的可转移性,为今后的研究提供洞察力。更多详情见https://gitee.com/djc ⁇ RICK/Attack-Transtiferable-On-Synthet-contryion。