用大模型自动生成真实攻击链，大幅缩短网络安全演练准备时间
AEGIS: White-Box Attack Path Generation using LLMs and Training Effectiveness Evaluation for Large-Scale Cyber Defence Exercises
- 用大模型+白盒访问动态发现漏洞，无需预先构建漏洞图谱
- 在46台主机的实战演习中，自动生成路径与人工设计效果相当
- 适合安全团队快速构建高仿真攻防演练场景
网络安全演练中的攻击路径构建需大量专家投入。现有自动化方法依赖预先整理的漏洞图谱或利用集合，适用范围受限。本文提出AEGIS系统，通过大模型、白盒访问及蒙特卡洛树搜索，在真实漏洞执行过程中动态生成攻击路径。大模型搜索可不依赖预设漏洞图谱发现攻击链，白盒访问允许在隔离环境中验证漏洞有效性。在涵盖46台主机的CIDeX 2025大规模演习中，AEGIS生成的攻击路径在感知学习、参与度、可信度和挑战性四个维度上与人工设计路径表现相当。评估使用经过验证的问卷，可扩展至通用仿真训练场景。AEGIS将攻击链发现与验证自动化，使场景开发周期从数月缩短至数天，使专家精力从技术验证转向场景设计。
原文摘要 · Abstract (English)
Creating attack paths for cyber defence exercises requires substantial expert effort. Existing automation requires vulnerability graphs or exploit sets curated in advance, limiting where it can be applied. We present AEGIS, a system that generates attack paths using LLMs, white-box access, and Monte Carlo Tree Search over real exploit execution. LLM-based search discovers exploits dynamically without pre-existing vulnerability graphs, while white-box access enables validating exploits in isolation before committing to attack paths. Evaluation at CIDeX 2025, a large-scale exercise spanning 46 IT hosts, showed that AEGIS-generated paths are comparable to human-authored scenarios across four dimensions of training experience (perceived learning, engagement, believability, challenge). Results were measured with a validated questionnaire extensible to general simulation-based training. By automating exploit chain discovery and validation, AEGIS reduces scenario development from months to days, shifting expert effort from technical validation to scenario design.
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。