徐文渊,冀晓宇*,闫琛,程雨诗.具身智能安全治理[J].中国科学院院刊,2025,40(3):429-439.

具身智能安全治理

Embodied artificial intelligence security and governance

徐文渊
浙江大学 电气工程学院 杭州 310027
XU Wenyuan
College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China
冀晓宇*
浙江大学 电气工程学院 杭州 310027
JI Xiaoyu*
College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China
闫琛
浙江大学 电气工程学院 杭州 310027
YAN Chen
College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China
程雨诗
浙江大学 电气工程学院 杭州 310027
CHENG Yushi
College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China

         具身智能;安全防护;安全治理

        embodied artificial intelligence (EAI);security;governance

        具身智能（EAI）作为下一个人工智能浪潮的重要方向，正逐步渗透到日常生活、工业生产、医疗健康乃至国防安全等领域。然而，组成具身智能复杂系统的硬件、软件、算法等都存在脆弱性，若被恶意攻击者利用，会对个人安全、社会安全甚至国家安全构成严重威胁。在此背景下，文章从具身智能信息域、物理域、社会域视角出发，围绕其本体安全、交互安全和应用安全3个层面，探讨具身智能的安全内涵与安全体系。同时，针对具身智能安全风险防范，文章提出具身智能的安全防护体系和综合治理措施，以期为具身智能的安全治理提供科学指导。

        Embodied artificial intelligence (EAI) is progressively integrated into the fabric of our daily lives, enhancing various sectors such as industrial production, healthcare, and national defense. Nevertheless, the diverse range of hardware devices, software algorithms, and data communications that constitute these complex systems may contain vulnerabilities that could be exploited by attackers, posing a serious threat to personal, social, and national security. Thus, this study examines the security implications and proposes a security framework of EAI, from the perspectives of the information domain, physical domain, and social domain, focusing on its ontological security, interaction security, and application security. To mitigate these security risks, this study proposes EAI security governance principles and comprehensive measures for EAI security, aiming to provide scientific guidance for effective governance in this area.