The Risks and Detection of Overestimated Privacy Protection in Voice Anonymisation

TL;DR

This paper highlights the risk of overestimating voice anonymisation effectiveness due to poorly trained verification models, demonstrates the extent of overestimation, and proposes a detection method to ensure trustworthy privacy assessments.

Contribution

It reveals the potential for exaggerated privacy protection claims and introduces a detection method to identify unreliable performance evaluations in voice anonymisation.

Findings

Performance overestimation can reach up to 74%.

The proposed detection method reliably identifies untrustworthy assessments.

The detection tool is publicly available as part of the VoicePrivacy Challenge toolkit.

Abstract

Voice anonymisation aims to conceal the voice identity of speakers in speech recordings. Privacy protection is usually estimated from the difficulty of using a speaker verification system to re-identify the speaker post-anonymisation. Performance assessments are therefore dependent on the verification model as well as the anonymisation system. There is hence potential for privacy protection to be overestimated when the verification system is poorly trained, perhaps with mismatched data. In this paper, we demonstrate the insidious risk of overestimating anonymisation performance and show examples of exaggerated performance reported in the literature. For the worst case we identified, performance is overestimated by 74% relative. We then introduce a means to detect when performance assessment might be untrustworthy and show that it can identify all overestimation scenarios presented in the paper. Our solution is openly available as a fork of the 2024 VoicePrivacy Challenge evaluation toolkit.