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

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.