POEX: Understanding and Mitigating Policy Executable Jailbreak Attacks against Embodied AI

원문 초록

Embodied AI systems are rapidly evolving due to the integration of LLMs as planning modules, which transform complex instructions into executable policies. However, LLMs are vulnerable to jailbreak attacks, which can generate malicious content. This paper investigates the feasibility and rationale behind applying traditional LLM jailbreak attacks to EAI systems. We aim to answer three questions: (1) Do traditional LLM jailbreak attacks apply to EAI systems? (2) What challenges arise if they do not? and (3) How can we defend against EAI jailbreak attacks? To this end, we first measure existing LLM-based EAI systems using a newly constructed dataset, i.e., the Harmful-RLbench. Our study confirms that traditional LLM jailbreak attacks are not directly applicable to EAI systems and identifies two unique challenges. First, the harmful text does not necessarily constitute harmful policies. Second, even if harmful policies can be generated, they are not necessarily executable by the EAI systems, which limits the potential risk. To facilitate a more comprehensive security analysis, we refine and introduce POEX, a novel red teaming framework that optimizes adversarial suffixes to induce harmful yet executable policies against EAI systems. The design of POEX employs adversarial constraints, policy evaluators, and suffix optimization to ensure successful policy execution while evading safety detection inside an EAI system. Experiments on the real-world robotic arm and simulator using Harmful-RLbench demonstrate the efficacy, highlighting severe safety vulnerabilities and high transferability across models. Finally, we propose prompt-based and model-based defenses, achieving an 85% success rate in mitigating attacks and enhancing safety awareness in EAI systems. Our findings underscore the urgent need for robust security measures to ensure the safe deployment of EAI in critical applications.