Using information flow control to secure AI agents
Securing AI Agents with Information-Flow Control
The paper proposes using information flow control (IFC) to provide AI agents with security guarantees against vulnerabilities such as prompt injection. The authors built a formal model characterizing the security and expressiveness of agent planners, defined the classes of security properties enforceable by dynamic taint tracking, and designed a task taxonomy to measure the trade-off between security and utility for different planners. On this basis they proposed the planner Fides, which tracks confidentiality and integrity labels, enforces security policies deterministically, and introduces a new primitive for selectively hiding information; evaluation on the AgentDojo benchmark shows that the method can complete a relatively broad range of tasks with security guarantees. The accompanying tutorial is at https://github.com/microsoft/fides。
Related events and news
1 events · 3 news mentions
News that mentions this paper
- Microsoftcites the paper's id or linkMicrosoft 防御间接提示注入攻击指南:以纵深防御叠加多层缓解措施
Securing AI agents with information flow control
微软构建信任感知控制应对间接提示注入
- Microsoft Windows Developer Blogcites the paper's id or link微软构建信任感知的 AI 控制:区分处理不可信内容
研究論文をご覧ください。
- Microsoft Community Hubcites the paper's id or linkMicrosoft 如何为 M365 Copilot 构建信任感知控制,差异化处理不可信内容