Targeting World Models to Compromise Robot Learning Pipelines
Researchers have identified a new vulnerability in robot learning pipelines that exploit world models. By injecting malicious prompts or compromising transition dynamics into seemingly safe datasets, attackers can create synthetic, dangerous training data. This data, when processed by a world model, can lead to the deployment of compromised robotic policies, even if the original ground truth data appears safe. AI
IMPACT Highlights a new attack vector that could compromise the safety and reliability of AI-powered robotic systems.