用相似度排名泄露评估语音匿名化隐私风险
Evaluating voice anonymisation using similarity rank disclosure
- 基于特征表示的相似度排名泄露，不依赖分类器阈值
- 在2024语音隐私挑战系统中发现EER遗漏的隐私漏洞
- 适合评估语音匿名化系统的平均与最坏情况泄露
语音匿名化评估仍具挑战性。现有方法依赖自动说话人验证指标（如等错误率EER），其性能估计受分类器和工作点影响，可能无法完整或产生误导性地刻画隐私风险。本文研究了基于信息论的相似度排名泄露（SRD）指标，该指标作用于特征表示而非分类决策，实现阈值无关的隐私评估，并可分析平均与最坏情况下的信息泄露。我们将其应用于2024年语音隐私挑战赛中的说话人嵌入、基频和音素嵌入系统。结果表明，SRD揭示了EER评估未能捕捉的隐私泄露和系统特定弱点。研究凸显了表示层指标的价值，展示了SRD作为灵活且可解释的语音匿名化评估工具的潜力。
原文摘要 · Abstract (English)
The evaluation of voice anonymisation remains challenging. Current practice relies on automatic speaker verification metrics such as the equal error rate (EER). Performance estimates dependent on the classifier and operating point provide an incomplete or even misleading characterisation of privacy risk. We investigate the use of similarity rank disclosure (SRD), an information-theoretic metric, which operates on feature representations rather than classifier decisions, providing a threshold-independent assessment of privacy and analysis of both average and worst-case disclosure. We report its application to speaker embeddings, fundamental frequency, and phone embeddings using 2024 VoicePrivacy Challenge systems. The SRD reveals privacy leaks and system-specific weaknesses missed by EER-based evaluation. Findings highlight the merit of representation-level metrics and demonstrate the potential of SRD as a flexible and interpretable tool for the evaluation of voice anonymisation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。