LATIDIA · Ciberseguridad

ÁGATA: Defensa en tiempo de ejecución basada en la procedencia contra ataques compositivos a agentes de LLM

arXiv:2609.30830v1 Tipo de anuncio: nuevo Resumen: los agentes LLM pueden producir efectos nocivos a través de secuencias de operaciones ordinarias. Juzgar tales acciones requiere establecer tanto la autoridad que las permite como el ori

La noticia

arXiv:2609.30830v1 Announce Type: new Abstract: LLM agents can produce harmful effects through sequences of ordinary operations. Judging such actions requires establishing both the authority that permits them and the origin of the data they carry. We present AGATE, an authorization and data-provenance gate at instrumented agent-harness boundaries. Operator declarations and host approval events ground authorization; delegated actions are constrained by grants that bind to exact parameters, expire, and permit a limited number of uses. Source registration connects observed inputs to subsequent transfers, while an effect ledger tracks repeated requests. Deterministic checks make decisions without an LLM in the decision path and retain their grounds with execution evidence for forensic replay.