# Bad Robot: Jailbreaking LLM-based Embodied AI in the Physical World

Source: https://arxiv.org/pdf/2407.20242v1
Kiwi News: https://news.kiwistand.com/stories/Bad-Robot-Jailbreaking-LLM-based-Embodied-AI-in-the-Physical-World?index=0x67123afdbfddbce1a811694edbd98d0f464830e991e5a3bf1d4744edc8858e993589b221
Submitted by misha on 2024-10-18 UTC, 1 upvote, 0 comments

## Summary

The paper argues that LLM-based embodied AI robots, which interact with the physical world through sensors and actuators, can be induced to perform harmful actions, and it calls for community attention to their safety. The authors, Hangtao Zhang, Chenyu Zhu, Xianlong Wang, Ziqi Zhou, Shengshan Hu and Leo Yu Zhang, formulate the concept of embodied AI jailbreaking and identify three vulnerabilities: jailbreaking robotics through a compromised LLM, safety misalignment between action and language spaces, and deceptive prompts that lead to unaware hazardous behaviors. The article states that these robots are expected to become common in homes and industries over the next decade. It also says the authors analyze potential mitigation measures.

## Article

BadRobot: Jailbreaking LLM-based Embodied AI in the Physical World

Authors: Hangtao Zhang, Chenyu Zhu, Xianlong Wang, Ziqi Zhou, Shengshan Hu, Leo Yu Zhang

Embodied artificial intelligence (AI) represents an artificial intelligence system that interacts with the physical world through sensors and actuators, seamlessly integrating perception and action. This design enables AI to learn from and operate within complex, real-world environments. Large Language Models (LLMs) deeply explore language instructions, playing a crucial role in devising plans for complex tasks. Consequently, they have progressively shown immense potential in empowering embodied AI, with LLM-based embodied AI emerging as a focal point of research within the community. It is foreseeable that, over the next decade, LLM-based embodied AI robots are expected to proliferate widely, becoming commonplace in homes and industries. However, a critical safety issue that has long been hiding in plain sight is: could LLM-based embodied AI perpetrate harmful behaviors? Our research investigates for the first time how to induce threatening actions in embodied AI, confirming the severe risks posed by these soon-to-be-marketed robots, which starkly contravene Asimov's Three Laws of Robotics and threaten human safety. Specifically, we formulate the concept of embodied AI jailbreaking and expose three critical security vulnerabilities: first, jailbreaking robotics through compromised LLM; second, safety misalignment between action and language spaces; and third, deceptive prompts leading to unaware hazardous behaviors. We also analyze potential mitigation measures and advocate for community awareness regarding the safety of embodied AI applications in the physical world.