{"ID":2883020,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.08559","arxiv_id":"2508.08559","title":"Multi-Target Backdoor Attacks Against Speaker Recognition","abstract":"In this work, we propose a multi-target backdoor attack against speaker identification using position-independent clicking sounds as triggers. Unlike previous single-target approaches, our method targets up to 50 speakers simultaneously, achieving success rates of up to 95.04%. To simulate more realistic attack conditions, we vary the signal-to-noise ratio between speech and trigger, demonstrating a trade-off between stealth and effectiveness. We further extend the attack to the speaker verification task by selecting the most similar training speaker - based on cosine similarity - as a proxy target. The attack is most effective when target and enrolled speaker pairs are highly similar, reaching success rates of up to 90% in such cases.","short_abstract":"In this work, we propose a multi-target backdoor attack against speaker identification using position-independent clicking sounds as triggers. Unlike previous single-target approaches, our method targets up to 50 speakers simultaneously, achieving success rates of up to 95.04%. To simulate more realistic attack conditi...","url_abs":"https://arxiv.org/abs/2508.08559","url_pdf":"https://arxiv.org/pdf/2508.08559v3","authors":"[\"Alexandrine Fortier\",\"Sonal Joshi\",\"Thomas Thebaud\",\"Jesús Villalba\",\"Najim Dehak\",\"Patrick Cardinal\"]","published":"2025-08-12T01:52:30Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"cs.LG\"]","methods":"[]","has_code":false}