AIBearisharXiv – CS AI · 8h ago7/10
🧠
From Prompt to Physical Actuation: Holistic Threat Modeling of LLM-Enabled Robotic Systems
Researchers present the first comprehensive threat modeling of LLM-enabled robotic systems, mapping three categories of attacks (cyber, adversarial, and conversational) across the perception-planning-actuation pipeline. The analysis reveals critical architectural vulnerabilities where compromised inputs or unsafe model outputs can propagate to unsafe physical actions without proper validation boundaries.