用声明文件定义防御智能体，让大模型安全可控地执行安全操作。
PocketAgents: A Manifest-Driven Library of Autonomous Defense Agents
- 通过声明、提示和运行时上下文三文件配置智能体，限定其行为边界。
- 18次闭环测试中13次成功阻断模拟暗面攻击，4次因格式不合规失败。
- 适合需要可验证、可扩展的自动化防御系统的安全团队使用。
将大语言模型（LLM）接入防御执行需超越简单判断攻击是否发生。防御者必须确定哪些模型输出可改变系统状态、哪些应被拒绝，以及如何记录失败。本文提出PocketAgents，一个基于声明文件的自主防御智能体库。每个智能体由三个数据文件构成：声明文件、提示文件和运行时上下文。共享运行时提供受控遥测访问，并仅接受在声明中明确定义动作的类型化报告。我们在网络对抗沙盒Perry上实现PocketAgents，评估了命令与控制及数据外传两个智能体，在模拟暗面攻击的小型企业拓扑中完成18次闭环测试。其中13次生成有效网络阻断动作并成功遏制攻击；4次因格式校验失败；1次生成有效无操作决策。实验表明，类型化边界使基于LLM的防御具备可测量性、可扩展性和可追溯性。
原文摘要 · Abstract (English)
Connecting large language models (LLMs) to defensive enforcement requires more than asking a model whether an attack is happening. A defender must decide which model outputs may change the system state, which outputs must be rejected, and how failures should be recorded. We present PocketAgents, a manifest-driven library of autonomous defense agents. Each agent is installed as three data files: a manifest, a prompt, and a runtime context. The shared runtime gives the agent bounded telemetry access and accepts only typed reports whose requested action appears in the manifest. We implemented PocketAgents on top of a cyber arena (Perry), a cyber-deception testbed, and evaluated two agents, Command and Control and Exfiltration, in 18 closed-loop trials of a DarkSide-inspired attack on a small enterprise topology. Thirteen trials produced validated network-block actions and contained the attack; four failed schema validation; one produced a valid no-action decision. The experiments show that a typed boundary makes LLM-driven defense measurable, extensible, and attributable.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。