{"ID":2867964,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.18413","arxiv_id":"2509.18413","title":"VoxGuard: Evaluating User and Attribute Privacy in Speech via Membership Inference Attacks","abstract":"Voice anonymization aims to conceal speaker identity and attributes while preserving intelligibility, but current evaluations rely almost exclusively on Equal Error Rate (EER) that obscures whether adversaries can mount high-precision attacks. We argue that privacy should instead be evaluated in the low false-positive rate (FPR) regime, where even a small number of successful identifications constitutes a meaningful breach. To this end, we introduce VoxGuard, a framework grounded in differential privacy and membership inference that formalizes two complementary notions: User Privacy, preventing speaker re-identification, and Attribute Privacy, protecting sensitive traits such as gender and accent. Across synthetic and real datasets, we find that informed adversaries, especially those using fine-tuned models and max-similarity scoring, achieve orders-of-magnitude stronger attacks at low-FPR despite similar EER. For attributes, we show that simple transparent attacks recover gender and accent with near-perfect accuracy even after anonymization. Our results demonstrate that EER substantially underestimates leakage, highlighting the need for low-FPR evaluation, and recommend VoxGuard as a benchmark for evaluating privacy leakage.","short_abstract":"Voice anonymization aims to conceal speaker identity and attributes while preserving intelligibility, but current evaluations rely almost exclusively on Equal Error Rate (EER) that obscures whether adversaries can mount high-precision attacks. We argue that privacy should instead be evaluated in the low false-positive...","url_abs":"https://arxiv.org/abs/2509.18413","url_pdf":"https://arxiv.org/pdf/2509.18413v2","authors":"[\"Efthymios Tsaprazlis\",\"Thanathai Lertpetchpun\",\"Tiantian Feng\",\"Sai Praneeth Karimireddy\",\"Shrikanth Narayanan\"]","published":"2025-09-22T20:57:48Z","proceeding":"cs.CR","tasks":"[\"cs.CR\",\"cs.LG\"]","methods":"[]","has_code":false}