论文标题
防御对抗性攻击的防御攻击
Defense Against Adversarial Attacks on Audio DeepFake Detection
论文作者
论文摘要
音频深击（DF）是使用深度学习创建的人为产生的话语，其主要目的是以一种令人信服的方式欺骗听众。它们的质量足以在安全和隐私方面构成严重威胁，包括新闻或诽谤的可靠性。已经提出了多种基于神经网络的方法来检测生成的语音，以防止威胁。在这项工作中，我们介绍了对抗性攻击的主题，该主题通过在输入数据中添加表面（难以发现人类）的变化来降低探测器的性能。我们的贡献包含在两种情况下（白框和可转让性），评估3个检测架构对对抗攻击的鲁棒性，并通过使用我们的新颖自适应训练执行的对抗性训练来增强它。此外，研究的一个架构之一是Rawnet3，据我们所知，我们首次适应了DeepFake检测。
Audio DeepFakes (DF) are artificially generated utterances created using deep learning, with the primary aim of fooling the listeners in a highly convincing manner. Their quality is sufficient to pose a severe threat in terms of security and privacy, including the reliability of news or defamation. Multiple neural network-based methods to detect generated speech have been proposed to prevent the threats. In this work, we cover the topic of adversarial attacks, which decrease the performance of detectors by adding superficial (difficult to spot by a human) changes to input data. Our contribution contains evaluating the robustness of 3 detection architectures against adversarial attacks in two scenarios (white-box and using transferability) and enhancing it later by using adversarial training performed by our novel adaptive training. Moreover, one of the investigated architectures is RawNet3, which, to the best of our knowledge, we adapted for the first time to DeepFake detection.
