English

Inference Attacks for X-Vector Speaker Anonymization

Cryptography and Security 2025-05-15 v1 Sound Audio and Speech Processing

Abstract

We revisit the privacy-utility tradeoff of x-vector speaker anonymization. Existing approaches quantify privacy through training complex speaker verification or identification models that are later used as attacks. Instead, we propose a novel inference attack for de-anonymization. Our attack is simple and ML-free yet we show experimentally that it outperforms existing approaches.

Keywords

Cite

@article{arxiv.2505.08978,
  title  = {Inference Attacks for X-Vector Speaker Anonymization},
  author = {Luke Bauer and Wenxuan Bao and Malvika Jadhav and Vincent Bindschaedler},
  journal= {arXiv preprint arXiv:2505.08978},
  year   = {2025}
}
R2 v1 2026-06-28T23:32:17.037Z