Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2509.14469 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908545265434624 |
|---|---|
| author | Seo, Seungmin Aulov, Oleg Phillips, P. Jonathon |
| author_facet | Seo, Seungmin Aulov, Oleg Phillips, P. Jonathon |
| contents | We use the term re-identification to refer to the process of recovering the original speaker's identity from anonymized speech outputs. Speaker de-identification systems aim to reduce the risk of re-identification, but most evaluations focus only on individual-level measures and overlook broader risks from soft biometric leakage. We introduce the Soft Biometric Leakage Score (SBLS), a unified method that quantifies resistance to zero-shot inference attacks on non-unique traits such as channel type, age range, dialect, sex of the speaker, or speaking style. SBLS integrates three elements: direct attribute inference using pre-trained classifiers, linkage detection via mutual information analysis, and subgroup robustness across intersecting attributes. Applying SBLS with publicly available classifiers, we show that all five evaluated de-identification systems exhibit significant vulnerabilities. Our results indicate that adversaries using only pre-trained models - without access to original speech or system details - can still reliably recover soft biometric information from anonymized output, exposing fundamental weaknesses that standard distributional metrics fail to capture. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14469 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Measuring Soft Biometric Leakage in Speaker De-Identification Systems Seo, Seungmin Aulov, Oleg Phillips, P. Jonathon Sound We use the term re-identification to refer to the process of recovering the original speaker's identity from anonymized speech outputs. Speaker de-identification systems aim to reduce the risk of re-identification, but most evaluations focus only on individual-level measures and overlook broader risks from soft biometric leakage. We introduce the Soft Biometric Leakage Score (SBLS), a unified method that quantifies resistance to zero-shot inference attacks on non-unique traits such as channel type, age range, dialect, sex of the speaker, or speaking style. SBLS integrates three elements: direct attribute inference using pre-trained classifiers, linkage detection via mutual information analysis, and subgroup robustness across intersecting attributes. Applying SBLS with publicly available classifiers, we show that all five evaluated de-identification systems exhibit significant vulnerabilities. Our results indicate that adversaries using only pre-trained models - without access to original speech or system details - can still reliably recover soft biometric information from anonymized output, exposing fundamental weaknesses that standard distributional metrics fail to capture. |
| title | Measuring Soft Biometric Leakage in Speaker De-Identification Systems |
| topic | Sound |
| url | https://arxiv.org/abs/2509.14469 |