LATIDIA · Robótica

Sabotaje silencioso: el estado interno desencadenó ataques de puerta trasera en sistemas robóticos alimentados por LLM

arXiv:2609.26184v1 Tipo de anuncio: nuevo Resumen: La integración de los Modelos de Lenguaje Grande (LLM) en los sistemas de control robótico está permitiendo una nueva generación de agentes autónomos capaces de razonamiento y planificación complejos.

La noticia

arXiv:2609.26184v1 Announce Type: new Abstract: The integration of Large Language Models (LLMs) into robotic control systems is enabling a new generation of autonomous agents capable of complex reasoning and planning. While this paradigm shift accelerates progress, it also introduces novel security risks that remain largely unexplored. Current research into LLM backdoors has focused on attacks triggered by external stimuli, such as specific words, visual objects, or environmental states. These attacks, while potent, overlook a more insidious class of vulnerability where the trigger is internal to the agent's own operational logic. This paper presents the first comprehensive study of history-based backdoor attacks on LLM-powered robotic systems. We demonstrate that an attacker