LATIDIA · Ciberseguridad
AudioTrace: detección de pertenencia a nivel de archivo para modelos de lenguaje grande de audio
arXiv:2611.21088v1 Tipo de anuncio: nuevo Resumen: El uso de grabaciones de audio disponibles públicamente para entrenar modelos de lenguaje grande (LLM) de audio plantea importantes problemas de privacidad y derechos de autor, pero una auditoría eficaz
WhatsApp ↗Telegram ↗
La noticia
arXiv:2611.21088v1 Announce Type: new Abstract: Significant privacy and copyright concerns are raised by the use of publicly available audio recordings to train audio large language models (LLMs), yet effective auditing methods remain limited. Existing membership inference attacks typically assume knowledge of complete training examples, including their associated textual supervision. In practice, however, audio recordings may be paired with privately generated transcripts, captions, or question-answer pairs that are unavailable to owners of the recordings. This motivates audio-file-level membership inference, which determines whether a recording was used for training without assuming knowledge of its training tasks and annotations. This paper provides the first systematic investigation of this challenge and introduces AudioTraceBench, a