LATIDIA · Ciberseguridad

Firmado pero no seguro: integridad de los requisitos en las transferencias de LLM multiagente

arXiv:2611.07483v1 Anuncio Tipo: nuevo Resumen: Los agentes de IA empresariales dividen cada vez más la solicitud de un usuario entre subagentes y fusionan sus resultados, y cada transferencia puede resumir, alterar o ignorar un requisito.

La noticia

arXiv:2611.07483v1 Announce Type: new Abstract: Enterprise AI agents increasingly split a user's request across subagents and merge their results, and each handoff can summarize away, alter or ignore a requirement. We report a preregistered study with synthetic, exactly scorable tasks comparing free-text, structured JSON and signed requirement-manifest handoffs: the orchestrator extracts each requirement as a verbatim quote plus a checkable predicate, code signs the manifest with HMAC-SHA256, and deterministic code verifies the merger's decision. With Qwen3-8B (1,440 trajectories, five threats), signed manifests cut unsafe commits under attack from 69.4% to 9.0% (60.4 pp, 95% CI [51.4, 69.4]) with no net loss of conformant commits relative to structured handoffs. Signing is