Privacy Attacks on Voice Anonymization Systems: Overview and Key Findings from the First VoicePrivacy Attacker Challenge

Computer Speech & Language

The First VoicePrivacy Attacker Challenge is an ICASSP 2025 SP Grand Challenge that focuses on evaluating attacker systems against a set of voice anonymization systems submitted to the VoicePrivacy 2024 Challenge. Training, development, and evaluation datasets were provided along with a baseline attacker. Participants developed their attacker systems in the form of automatic speaker verification systems and submitted their scores on the development and evaluation data. 11 teams submitted 55 attackers targeting 7 anonymization systems. The best attacker systems reduced the equal error rate (EER) by 25%–44% relative to the baseline. Beyond global EER, analyses based on linkability and speaker-level risk show substantial variability in privacy protection across speakers and changes in anonymization system rankings under stronger attacks.

ソースコード：https://github.com/Voice-Privacy-Challenge/Voice-Privacy-Challenge-2024