# Inference Attacks for X-Vector Speaker Anonymization

arXiv: https://arxiv.org/abs/2505.08978 · HTML: https://mlsanity.com/paper/2505.08978/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 May 2025.

## Built on by (most cited first, 2 of 2)

- [SegReConcat: A Data Augmentation Method for Voice Anonymization Attack](https://mlsanity.com/paper/2508.18907/) (2025)
- [Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models](https://mlsanity.com/paper/2607.16870/) (2026)

## Abstract (arXiv)

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.