Work

Inference Attacks for X-Vector Speaker Anonymization

Year: 2025

Type: conference-paper

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.

Source: IEEE Security and Privacy Workshops (SPW)

DOI: 10.1109/spw67851.2025.00020

Authors: Luke A. Bauer, Wenxuan Bao, Malvika Jadhav, Vincent Bindschaedler

Institution: University of Florida

Language: English

Topic: Privacy-Preserving Technologies in Data

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Science Foundation

Award: SaTC: CORE: Medium: Securing the Voice Processing Pipeline Against Adversarial Audio