认证委托与授权 AI 智能体
Authenticated Delegation and Authorized AI Agents
AI总结:
针对自主 AI 智能体的授权与问责问题,论文提出基于 OAuth 2.0 和 OpenID Connect 扩展的可认证、可审计委托框架,并将自然语言权限转为访问控制策略。
摘要:
自主 AI 智能体的快速部署在数字空间中引发了围绕授权、问责和访问控制的紧迫挑战。需要制定新标准,以了解 AI 智能体代表谁行事,并恰当指导其使用,从而在保护在线空间的同时,释放向自主智能体委托任务的价值。我们提出一种新颖的框架,用于向 AI 智能体进行经过认证、获得授权且可审计的权限委托;在该框架中,人类用户可以安全地委托并限制智能体的权限和作用范围,同时保持清晰的问责链。该框架建立在现有身份识别与访问管理协议之上,通过面向智能体的凭证和元数据扩展 OAuth 2.0 与 OpenID Connect,并与既有认证和 Web 基础设施保持兼容。此外,我们提出一个框架,将灵活的自然语言权限转换为可审计的访问控制配置,从而能够在多种交互模态下稳健限定 AI 智能体的能力范围。总体而言,这种实用方法有助于立即部署 AI 智能体,同时解决关键的安全与问责问题,致力于确保智能体式 AI 系统只执行适当动作,并为数字服务提供商提供一种工具,使其能够支持 AI 智能体交互,而无需承担规模化交互造成损害的风险。
英文摘要:
The rapid deployment of autonomous AI agents creates urgent challenges around authorization, accountability, and access control in digital spaces. New standards are needed to know whom AI agents act on behalf of and guide their use appropriately, protecting online spaces while unlocking the value of task delegation to autonomous agents. We introduce a novel framework for authenticated, authorized, and auditable delegation of authority to AI agents, where human users can securely delegate and restrict the permissions and scope of agents while maintaining clear chains of accountability. This framework builds on existing identification and access management protocols, extending OAuth 2.0 and OpenID Connect with agent-specific credentials and metadata, maintaining compatibility with established authentication and web infrastructure. Further, we propose a framework for translating flexible, natural language permissions into auditable access control configurations, enabling robust scoping of AI agent capabilities across diverse interaction modalities. Taken together, this practical approach facilitates immediate deployment of AI agents while addressing key security and accountability concerns, working toward ensuring agentic AI systems perform only appropriate actions and providing a tool for digital service providers to enable AI agent interactions without risking harm from scalable interaction.
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。