arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2607.02605cs.SE
收藏

大语言模型驱动的渗透测试综述:分类法、共同演化及开放挑战

A Survey of LLM-Driven Penetration Testing: Taxonomy, Co-Evolution, and Open Challenges

University of Electronic Science and Technology of China(电子科技大学);The Hong Kong Polytechnic University(香港理工大学);Nanyang Technological University(南洋理工大学);Four-dimensional Powerise Technology Development Co., Ltd(四维力思科技发展有限公司);Jiangxi Academy of Cyber Security(江西省网络安全研究院)

Zheyuan He, Jiaxun Dong, Zihao Li, Ting Chen, Gelei Deng, Feng Luo, Jinkun Ji, Yuanlong Cao, Xiapu Luo

AI总结:

通过系统分析2023至2026年间81篇论文,梳理大语言模型驱动的渗透测试文献分类,追溯架构四阶段演化,指出关键发现,识别出评估可靠性等三个开放挑战。

摘要:

基于大语言模型的自主渗透测试系统Agents4Pentest是安全研究中快速发展的领域。本文通过对81篇论文的系统分析,解决该领域缺乏统一分类法等问题。将文献分为六类,追溯架构四阶段演化,得出关键发现,并识别出三个开放挑战。

英文摘要:

Agents4Pentest, an emerging class of LLM-based autonomous penetration testing systems, has become a rapidly growing area in security research. Despite this growth, the field still lacks a unified taxonomy, a systematic understanding of how agent architectures and evaluation benchmarks have co-evolved, and a clear characterization of remaining capability and reliability gaps. This survey addresses these gaps through a systematic analysis of 81 papers between 2023 and 2026. We organize the literature into six categories: evaluation benchmarks, general-purpose systems, domain-specific frameworks, CTF-based systems, defense-oriented research, and surveys. We further trace a four-phase architectural evolution from text-only reasoning agents to agents trained with Reinforcement Learning with Verifiable Rewards (RLVR), showing that each transition is driven by a distinct capability bottleneck. Our analysis yields several key findings. First, RLVR marks a shift in capability acquisition from imitation of expert demonstrations to reward-driven self-improvement, enabling agents to discover previously undocumented attack strategies. Second, CTF platforms have evolved from evaluation testbeds into dual-purpose infrastructure for both agent evaluation and RL training. Third, domain-specific frameworks improve efficiency through recurring specialization mechanisms, but their gains remain largely confined to narrow task classes and are difficult to compare across domains because existing evaluations rely on different benchmarks. Fourth, the field is expanding beyond offensive automation toward adversarial defense and security compliance. Across these categories, we identify three structurally linked open challenges: evaluation reliability, limited performance on multi-stage attack scenarios, and scarcity of high-quality training data.

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。

↑