Answers are grounded in this paper and cite their sources.
Proposed simple, machine learning-free inference attack improves de-anonymization in speaker models, suggesting privacy challenges.
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.
No takes yet. Share an insight, caveat, or question.
Bauer et al. (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: