人工智能发展和安全并重的法治探究——以人形机器人为例  

Legal Exploration of Balancing AI Development and Security

作　　者：刘权[1] Liu Quan

机构地区：[1]中央财经大学法学院

出　　处：《东方法学》2024年第5期32-42,共11页Oriental Law

摘　　要：基于“大数据+高算力+强算法”的人形机器人,能够实现连贯高效的人—机—环境智能交互,可服务特种领域需求,助力智能制造,成为人类生活助手和情感伴侣。尽管人形机器人存在功能安全、网络安全、个人信息安全、数据安全、国家安全、违法“代理”、侵权、伦理等多种风险,但如果过度追求安全,就会扼杀创新而阻碍发展。发展是安全的基础,安全是发展的条件,应实现人工智能发展和安全并重。通过理性实施包容审慎监管,推动人形机器人在发展中规范、在规范中发展。科学合理地开展安全风险评估,将人形机器人风险控制在可接受的水平。完善数据安全认证、个人信息保护认证等第三方声誉评价机制,并分级分类推动人形机器人标准制定。应合理配置相关主体的责任,避免人形机器人的过度拟人化,防止陷入“人形机器人陷阱”。通过完善的伦理规范约束人工智能研发者,并为人形机器人“加载”道德,使其对人和环境友好。Humanoid robots based on"big data+high computing power+strong algorithm"can achieve coherent and efficient human-machine-environment intelligent interaction,which can serve the needs of special fields,help intelligent manufacturing,and become human life assistants and emotional partners.Although humanoid robots have many risks such as functional security,network security,personal information security,data security,national security,illegal"agents",infringement,ethics,etc.,excessive pursuit of security will stifle innovation and hinder development.Development is the basis of security,security is the condition of development,we should achieve artificial intelligence development and security.Through the rational implementation of inclusive prudential supervision,humanoid robots are standardized in their development and develop in norms.Scientific and reasonable safety risk assessment is carried out to control the safety of humanoid robots at an acceptable level.Improve third-party reputation evaluation mechanisms such as data security certification and personal information protection certification,and promote the development of humanoid robot standards through classification.The responsibilities of relevant subjects should be reasonably allocated to avoid excessive anthropomorphism of humanoid robots to prevent falling into the"humanoid robot trap".Binding AI developers through sound ethical codes and"loading"humanoid robots with ethics to make them friendly to people and the environment.

关 键 词：人形机器人 具身智能 发展和安全并重 包容审慎监管 算法 安全风险评估 

分 类 号：DF0[政治法律—法学理论]