谷歌研究:智能体隐私与安全的开放难题
AI 总结
谷歌研究博客发布报告,提出从系统、模型、用户与生态多个层面应对智能体的隐私与安全风险。系统层主张在沙箱中动态限制智能体能力、建立智能体身份,并按情境变化授权或撤销数据访问;模型层则需让智能体判断分享用户数据等行为是否恰当,并澄清含糊的用户指令。报告还提出以动态、情境化、个性化的控制替代假设可预见性的“通知与选择”框架,并为多智能体协作设置防止串通违规的护栏,同时在生态治理层面研究情境规范的收集共享、冲突解决与合规验证。
深度见解
报告指出,自主智能体的行为本质上是概率性、高频且生成式的,而传统“通知与选择”框架依赖可预见性假设,因此需要转向动态、情境化的用户控制机制。
Multi-layered approach to agentic privacy and security
Working towards contextual policy engines together with necessary advances at the model- and user-level results in a multi-layered approach. Our report outlines opportunities for innovation across the entire stack:
- System-level sandboxing: The execution environment can impose additional guardrails to limit the impact of agent or model failures and facilitate detection and response. Traditional operating systems sandbox applications by statically limiting access, say to files or networks. For agents, we explore dynamically limiting agentic capabilities, establishing agent identity, and authorizing or revoking access to data based on changes in context.
- Model-level reasoning: An agent performing complex tasks has to judge the appropriateness of its actions, such as sharing user data. Future research should enable models to disambiguate under-specified user prompts and reason about appropriateness under changing contextual norms.
- User-centric controls: The traditional “Notice and Choice” framework assumes that individuals can make fine-grained decisions about actions affecting personal data and relies on an assumption of foreseeability. However, autonomous agents’ behavior is inherently probabilistic, high volume, and generative. We explore shifting interfaces towards dynamic, contextual, and personalized control mechanisms consistent with user mental models.
- Multi-agent interactions: So that AI agents can safely collaborate with each other on complex tasks we need to develop effective guardrails to prevent the agents from colluding and violating contextual norms.
- Ecosystem governance: We explore challenges in governance mechanisms to arrive at a set of contextual norms that are collected and shared across agents. Furthermore, as norms can differ across domains and entities we need mechanisms that allow us to resolve conflicts, negotiate norm changes, and verify compliance.