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.
@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}
}