LATIDIA · Robótica

Mienten rara vez, mienten a lo grande: sigilosos ataques internos a equipos de robots LLM

arXiv:2610.04744v1 Tipo de anuncio: nuevo Resumen: Cuando un equipo de robots delega la planificación y la confianza mutua a los agentes de LLM, un solo robot comprometido puede corromper el resultado compartido. Estudiamos esta amenaza en una tarea fundamentada:

La noticia

arXiv:2610.04744v1 Announce Type: new Abstract: When a team of robots delegates planning and mutual trust to LLM agents, a single compromised robot can corrupt the shared outcome. We study this threat in a grounded task: a multi-robot survey in which measurements can be verified against the physical world, but every verification costs budget that would otherwise advance the mission. We treat the compromised robot as a stealthy adversary in the system-theoretic sense: it is limited not by an energy bound but by the team's own detectors. We then derive two bounds. First, the probability that the adversary's reports are verified is bounded below in terms of the degrees in the