新闻
Agentic Permissions Policy Algebra for Taint Confinement in LLM Agents
arXiv cs.AI · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- Researchers presented APPA, an information flow control framework that lets LLM agents safely inspect untrusted data without permanently tainting their working context.
- 为何重要
- Engineers building autonomous agents that handle mixed-confidentiality data and need to balance security against prompt injection with practical utility.
- 注意
- Framework is evaluated on four models with varying results; three showed utility recovery but one did not, suggesting generalization remains an open question.
收听本摘要
文章节选
-->
Computer Science > Cryptography and Security
arXiv:2607.24625v1 (cs)
[Submitted on 27 Jul 2026]
Title: Agentic Permissions Policy Algebra for Taint Confinement in LLM Agents
Authors: Arseny Kravchenko , Vadim Liventsev , Innokentii Konstantinov , Ildar Iskhakov , Matvey Kukuy
View a PDF of the paper titled Agentic Permissions Policy Algebra for Taint Confinement in LLM Agents, by Arseny Kravchenko and 4 other authors
View PDF HTML (experimental)
Abstract: Autonomous LLM agents processing mixed-confidentiality data face severe security risks from prompt injection attacks and reasoning errors. While dynamic Information Flow Control (IFC) provides structural security guarantees, traditional taint tracking permanently taints an agent's context upon reading unvetted data, severely restricting downstream utility. We present APPA (Agentic Permissions Policy Algebra), an IFC framework that resolves this usability bottleneck through engine-managed context branching and prospective acquisition enforcement. Before data acquisition occurs, APPA prospectively evaluates label descents and missing prerequisites, generating actionable remedy plans (Authorize, Accept). To inspect unvetted data without polluting the primary context, a label-seeded child trajectory is spawned, absorbing label descent locally and allowing a trusted sanitizer to return a bounded derivative to the unchan
节选自原文。请前往来源阅读全文。
- agent
- agentic
- llm
- reasoning
- prompt
The Agent Architect
每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。
每周一封邮件,一键退订。您的地址仅用于发送简报。