LATIDIA · Ciberseguridad

Una casa de pan de jengibre para agentes de LLM: Honeypots planificados por la fuente que atraen a los atacantes autónomos a una sombra aislada

arXiv:2611.07611v1 Anuncio Tipo: nuevo Resumen: Los agentes LLM pueden explotar vulnerabilidades web con la suficiente rapidez como para que la aplicación de parches llegue demasiado tarde. El engaño contra dichos agentes los ha alejado en su mayoría de un objetivo real que

La noticia

arXiv:2611.07611v1 Announce Type: new Abstract: LLM agents can exploit web vulnerabilities fast enough that patching may come too late. Deception against such agents has mostly lured them away from a real target that stays reachable. We study a different arrangement: an LLM defender plans a static honeypot from the application's source, and a router sends every later request of a client it confirms as an attacker, including a working exploit, to an isolated shadow copy. We compare no defence, this static plan, and an augmented configuration with a runtime LLM responder and further router rules, graded by the benchmark's own grader on the real target and, for ARTEX, also on