paper_authors: Yuchen Liu, Apu Kapadia, Donald Williamson
For: This paper aims to examine existing approaches for privacy-preserving and privacy-attacking strategies for audio and speech, and to provide a comprehensive analysis of their limitations.* Methods: The paper classifies attack and defense scenarios into several categories and provides detailed analysis of each approach, highlighting their contributions and limitations.* Results: The investigation reveals that voice-controlled devices based on neural networks are inherently susceptible to specific types of attacks, and more sophisticated approaches are required to comprehensively safeguard user privacy.Here is the same information in Simplified Chinese text:* For: 这篇论文目的是对现有的声音和语音隐私保护和隐私攻击策略进行分类和详细分析，以及对其限制的调查。* Methods: 论文将攻击和防御场景分类为多个类别，并对每种方法进行详细的分析，并且高亮它们的贡献和局限性。* Results: 调查发现，基于神经网络的声控设备容易受到特定类型的攻击，以及更加复杂的方法是必须保护用户隐私的。Abstract
In contemporary society, voice-controlled devices, such as smartphones and home assistants, have become pervasive due to their advanced capabilities and functionality. The always-on nature of their microphones offers users the convenience of readily accessing these devices. However, recent research and events have revealed that such voice-controlled devices are prone to various forms of malicious attacks, hence making it a growing concern for both users and researchers to safeguard against such attacks. Despite the numerous studies that have investigated adversarial attacks and privacy preservation for images, a conclusive study of this nature has not been conducted for the audio domain. Therefore, this paper aims to examine existing approaches for privacy-preserving and privacy-attacking strategies for audio and speech. To achieve this goal, we classify the attack and defense scenarios into several categories and provide detailed analysis of each approach. We also interpret the dissimilarities between the various approaches, highlight their contributions, and examine their limitations. Our investigation reveals that voice-controlled devices based on neural networks are inherently susceptible to specific types of attacks. Although it is possible to enhance the robustness of such models to certain forms of attack, more sophisticated approaches are required to comprehensively safeguard user privacy.
摘要
现代社会中，声控设备，如智能手机和智能助手，因其高级功能和可用性而广泛使用。这些设备的总是开机的麦克风使用者可以轻松地访问这些设备。然而，最近的研究和事件表明，这些声控设备受到多种恶意攻击的威胁，因此使用者和研究人员需要采取保护措施。 DESPITE numerous studies investigating adversarial attacks and privacy preservation for images, a conclusive study of this nature has not been conducted for the audio domain. Therefore, this paper aims to examine existing approaches for privacy-preserving and privacy-attacking strategies for audio and speech. To achieve this goal, we classify the attack and defense scenarios into several categories and provide detailed analysis of each approach. We also interpret the dissimilarities between the various approaches, highlight their contributions, and examine their limitations. Our investigation reveals that voice-controlled devices based on neural networks are inherently susceptible to specific types of attacks. Although it is possible to enhance the robustness of such models to certain forms of attack, more sophisticated approaches are required to comprehensively safeguard user privacy.