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
备注:
2026 AAAI Summer Symposium on Human-Aware AI Agents for the Cyber Battlefield
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.
Incident Response Planning Using a Lightweight Large Language Model with Reduced Hallucination
Department of Electrical and Electronic Engineering, University of Melbourne, Australia(墨尔本大学电子与电气工程系);Department of Computing, Imperial College London, United Kingdom(伦敦帝国理工学院计算机系)
IoTEdu: Access Control, Detection, and Automatic Incident Response in Academic IoT Networks
IComp, Universidade Federal do Amazonas (UFAM)(IComp,亚马逊联邦大学);AI Horizon Labs, Programa de Pós-Graduação em Engenharia de Software (PPGES) Universidade Federal do Pampa (UNIPAMPA)(AI Horizon Labs,软件工程硕士项目,潘帕斯联邦大学)
SoK: A Taxonomy for Cybersecurity Incident Response Influence Factors
FH Münster University of Applied Sciences(明斯特应用科学大学);Fraunhofer SIT and National Research Center for Applied Cybersecurity ATHENE(弗劳恩霍夫SIT和应用网络安全国家研究中心ATHENE);Graduate School for Applied Research in North Rhine-Westphalia (Graduate School NRW)(北莱茵-威斯特法伦州应用研究研究生院);International Computer Science Institute, UC Berkeley(加州大学伯克利分校国际计算机科学研究所)
PHOENI2X -- A European Cyber Resilience Framework With Artificial-Intelligence-Assisted Orchestration, Automation and Response Capabilities for Business Continuity and Recovery, Incident Response, and Information Exchange
A Competing-Hazards Systematization of Loss of Control in Autonomous Agents
Centre for Intelligent Cloud Computing, CoE for Advanced Cloud, Faculty of Information Science and Technology, Multimedia University(多媒体大学信息科学与技术学院先进云卓越中心智能云计算中心)
Consistent and Compatible Modelling of Cyber Intrusions and Incident Response Demonstrated in the Context of Malware Attacks on Critical Infrastructure
Accelerating Incident Response: A Hybrid Approach for Data Breach Reporting
IMT School for Advanced Studies Lucca(卢卡高等研究学院);University of Cagliari(卡利亚里大学);University of Salerno(萨莱诺大学);Sant’Anna School of Advanced Studies(圣安娜高等研究学院);University of Camerino(卡梅里诺大学)