LATIDIA · Ciberseguridad

VEPA: Política formal de evolución verificada para barandas de agentes LLM de por vida

arXiv:2610.12813v1 Announce Type: cross Resumen: Los agentes de LLM operan cada vez más sobre recursos sensibles, como documentos privados y estados mutables del sistema, lo que puede crear graves riesgos de seguridad. Tiempo de ejecución

La noticia

arXiv:2610.12813v1 Announce Type: cross Abstract: LLM agents increasingly operate over sensitive resources, such as private documents and mutable system states, which can create serious safety and security risks. Runtime guardrails should therefore make inspectable, reproducible, and deterministic allow or refuse decisions before potentially irreversible agent actions are executed. However, safety and security requirements are rarely complete before deployment, so guardrails need to keep adapting as new risks emerge. Existing adaptive guardrails learn from deployment experience, but they usually apply safety policies through LLM inference, which can lead to inconsistent decisions and ambiguous policy interpretations. Formal guardrails, on the other hand, enforce policies deterministically, but they usually rely on pre-deployment or