LATIDIA · Ciberseguridad
La medida de protección ha funcionado. ¿Es más seguro el sistema LLM?
arXiv:2609.00519v2 Tipo de anuncio: sustitución Resumen: Las medidas de protección de los servicios de modelos lingüísticos grandes suelen evaluarse en función de sus tasas de bloqueo de ataques en conjuntos de pruebas. Las decisiones de implementación también dependen de la cantidad de contenido dañino
WhatsApp ↗Telegram ↗
La noticia
arXiv:2609.00519v2 Announce Type: replace Abstract: Safeguards for large language model services are typically evaluated by their attack-blocking rates on test suites. Deployment decisions also depend on how much harmful assistance attackers can still obtain from the system, which these rates do not measure. To determine what published evaluations establish about deployment safety, we develop a framework that translates reported results into the minimum and maximum harmful assistance that can remain under a specified outcome and threat model. For safeguards that block attacks through a check, we show that the most an attacker can obtain depends on three properties: whether attack paths pass through the check, its miss rate against every