arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.13156cs.CRcs.AI
收藏

上下文自主网络事件响应:一种端到端的大语言模型代理方法

In-Context Autonomous Network Incident Response: An End-to-End Large Language Model Agent Approach

Department of Systems Engineering, City University of Hong Kong(香港城市大学系统工程系);Department of Electrical and Electronic Engineering, University of Melbourne(墨尔本大学电子与电气工程系)

Yiran Gao, Kim Hammar, Tao Li

AI总结:

本文提出一种端到端的大语言模型代理方法,通过整合感知、推理、规划和行动功能,实现网络事件响应的自主学习与适应,实验表明其恢复效率比前沿模型快23%。

摘要:

快速演变的网络攻击要求能够自主学习和适应变化威胁的事件响应系统。先前工作广泛探索了强化学习方法,通过大量模拟事件来学习响应策略。尽管这种方法有效,但需要手工建模模拟器并压制了原始系统日志和警报中的有用语义。为了解决这些限制,我们提出利用大语言模型(LLM)预训练的安全知识和上下文学习,创建事件响应规划的端到端代理解决方案。具体而言,我们的代理将感知、推理、规划和行动四种功能整合到一个轻量级LLM(14B模型)中。通过微调和链式推理,我们的LLM代理能够处理系统日志并推断底层网络状态(感知),更新其攻击模型的猜测(推理),模拟不同响应策略下的后果(规划),并生成有效的响应(行动)。通过将LLM模拟结果与实际观察进行比较,LLM代理不断改进其攻击猜测和相应响应,从而展示出上下文适应性。我们的代理方法无需建模,可在商用硬件上运行。当在文献中报告的事件日志上评估时,我们的代理恢复速度比前沿LLM快高达23%。

英文摘要:

Rapidly evolving cyberattacks demand incident response systems that can autonomously learn and adapt to changing threats. Prior work has extensively explored the reinforcement learning approach, which involves learning response strategies through extensive simulation of the incident. While this approach can be effective, it requires handcrafted modeling of the simulator and suppresses useful semantics from raw system logs and alerts. To address these limitations, we propose to leverage large language models' (LLM) pre-trained security knowledge and in-context learning to create an end-to-end agentic solution for incident response planning. Specifically, our agent integrates four functionalities, perception, reasoning, planning, and action, into one lightweight LLM (14b model). Through fine-tuning and chain-of-thought reasoning, our LLM agent is capable of processing system logs and inferring the underlying network state (perception), updating its conjecture of attack models (reasoning), simulating consequences under different response strategies (planning), and generating an effective response (action). By comparing LLM-simulated outcomes with actual observations, the LLM agent repeatedly refines its attack conjecture and corresponding response, thereby demonstrating in-context adaptation. Our agentic approach is free of modeling and can run on commodity hardware. When evaluated on incident logs reported in the literature, our agent achieves recovery up to 23% faster than those of frontier LLMs.

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。

↑