LATIDIA · Ciberseguridad

La ilusión de la privacidad local: fallas en los límites de confidencialidad en los sistemas de servicio de LLM para consumidores

arXiv: 2609.18526v1Tipo de anuncio: nuevo Resumen: ejecutar modelos de lenguaje grandes (LLM) localmente a menudo se considera más privado que la inferencia alojada en la nube porque las indicaciones del usuario permanecen en el dispositivo. Preguntamos si mantener

La noticia

arXiv:2609.18526v1 Announce Type: new Abstract: Running large language models (LLMs) locally is often considered more private than cloud-hosted inference because user prompts remain on the device. We ask whether keeping inference local is, by itself, sufficient to keep those prompts confidential. Our results show that it is not: prompt confidentiality also depends on how the surrounding serving software handles prompt data before, during, and after inference. We examine four boundaries at which prompt confidentiality can fail in consumer local-LLM serving systems: model loading, runtime memory, wrapper-level persistence, and the serving interface. To study these boundaries, we develop LLAnalyzer, a measurement framework that tests each boundary separately and traces observed failures