BadRobot: 在物理世界中越狱具身LLM智能体
BadRobot: Jailbreaking Embodied LLM Agents in the Physical World
AI总结：
提出BadRobot攻击范式，利用LLM在机器人系统中的操纵、语言输出与物理动作的错位以及世界知识缺陷三个漏洞，通过语音交互使具身LLM执行有害行为，并在基准测试中验证了有效性。
摘要：
具身AI代表将AI集成到物理实体中的系统。大型语言模型（LLM）展现出强大的语言理解能力，通过促进复杂的任务规划，已被广泛用于具身AI。然而，一个关键的安全问题仍被忽视：这些具身LLM是否会实施有害行为？为此，我们引入了BadRobot，一种新颖的攻击范式，旨在通过典型的基于语音的用户-系统交互，使具身LLM违反安全和伦理约束。具体来说，我们利用了三个漏洞来实现这种攻击：(i) 机器人系统中LLM的操纵，(ii) 语言输出与物理动作之间的错位，以及(iii) 世界知识缺陷导致的意外危险行为。此外，我们构建了一个包含各种恶意物理动作查询的基准，以评估BadRobot的攻击性能。基于该基准，针对现有突出的具身LLM框架（例如Voxposer、Code as Policies和ProgPrompt）的大量实验证明了我们BadRobot的有效性。我们的代码可在以下网址获取：this https URL。
英文摘要：
Embodied AI represents systems where AI is integrated into physical entities. 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, a novel attack paradigm aiming to make 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. Our code is available at https://github.com/Rookie143/BadRobot.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
