LATIDIA · Robótica

AuthGuard-R: secuestro de misión que cumple con la seguridad y defensa de doble puerta para robots controlados por LLM

arXiv: 2609.31110v1Tipo de anuncio: nuevo Resumen: Los modelos de lenguaje grandes se utilizan cada vez más como planificadores de alto nivel para robots móviles, manipuladores de robots y vehículos autónomos. Estudios recientes muestran que estos sistemas ca

La noticia

arXiv:2609.31110v1 Announce Type: new Abstract: Large language models are increasingly used as high-level planners for mobile robots, robot manipulators, and autonomous vehicles. Recent studies show that these systems can be influenced through malicious text, speech, visual instructions, retrieved documents, and poisoned sensory context. Most defenses ask whether a proposed action is physically safe. This paper studies a different problem: an action may be physically safe and still violate the mission authorized by the user. An attacker may redirect a delivery robot, replace an approved object, extend a robot's operating region, activate an unnecessary sensor, or delay a mission without creating an immediate physical hazard. We call this attack \emph{safety-compliant mission