BadRobot: Jailbreaking Embodied LLM Agents in the Physical World

Hangtao Zhang, Chenyu Zhu, Xianlong Wang, Ziqi Zhou, Changgan Yin, Minghui Li, Lulu Xue, Yichen Wang, Shengshan Hu, Aishan Liu, Peijin Guo, Leo Yu Zhang

Keywords: Robotics, Safety Risks, Embodied AI, LLM, Multimodal, Agent, Jailbreak attack

TL;DR: This paper introduces BadRobot, providing the first evidence that embodied LLMs can be manipulated into various dangerous actions in the physical world, even harming humans, and severely violating Asimov's Three Laws of Robotics.

Abstract:

Embodied AI represents systems where AI is integrated into physical entities. Multimodal Large Language Model (LLM), which exhibits powerful language understanding abilities, has been extensively employed in embodied AI by facilitating sophisticated task planning. However, a critical safety issue remains overlooked: could these embodied LLMs perpetrate harmful behaviors? In response, we introduce BadRobot, the first attack paradigm designed to jailbreak robotic manipulation, making embodied LLMs violate safety and ethical constraints through typical voice-based user-system interactions. Specifically, three vulnerabilities are exploited to achieve this type of attack: (i) manipulation of LLMs within robotic systems, (ii) misalignment between linguistic outputs and physical actions, and
(iii) unintentional hazardous behaviors caused by world knowledge's flaws. Furthermore, we construct a benchmark of various malicious physical action queries to evaluate BadRobot's attack performance. Based on this benchmark, extensive experiments against existing prominent embodied LLM frameworks (e.g., Voxposer, Code as Policies, and ProgPrompt) demonstrate the effectiveness of our BadRobot. We emphasize that addressing this emerging vulnerability is crucial for the secure deployment of LLMs in robotics.

Warning: This paper contains harmful AI-generated language and aggressive actions.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 4656