arXiv cs.CL· Ruoyu Wang, Heng Zhao, Renjie Wu, Tianhang Zheng, Mengnan Zhao, Wanyu Lin, Kui Ren·· 12 小时前AI 评分38
AgentSnare：用轨迹自适应欺骗环境延迟、转移并化解自主 Web 渗透智能体
AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Web Penetration Agents
AI 导读
AgentSnare 是一个轨迹自适应欺骗系统，通过随探索扩展的诱饵环境对抗 LLM 渗透智能体。其 ShadowOS 结合 LLM 驱动的诱饵构造器与虚拟内核，并用离线对抗交互模拟框架训练小模型替代昂贵的大 LLM。
正文 · 原文
Abstract:Large language model agents automate web penetration testing through observation-action loops, enabling defenders to influence decisions with deceptive decoy observations. Advanced agents can recognize and bypass static decoys, then refocus on real targets. We propose AgentSnare, a trajectory-adaptive deception system that expands a decoy environment alongside exploration. For online deployment, ShadowOS combines an LLM-driven decoy constructor with a virtual kernel. Conditioned on exploration, it generates decoy artifacts that the kernel materializes and handles consistently across interactions, sustaining long-horizon exploration. Because deploying a powerful LLM for decoy construction is costly and slow, we train a small LLM using an offline adversarial interaction-simulation framework. It synthesizes multi-round trajectories by generating candidates and retaining those that sustain simulated interactions. Across 15 CVE-Bench web applications and four attacker models, AgentSnare absorbs 49.9% of tool calls to delay attacks, retains 57.2% of post-entry actions in the decoy to divert trajectories, and grounds 89.5% of completion reports in decoy evidence to defuse threats; across 60 attacker-CVE pairs, no real target is exploited at pass@3.
| Subjects: | Cryptography and Security (cs.CR); Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2607.26998 [cs.CR] |
| (or arXiv:2607.26998v5 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2607.26998 arXiv-issued DOI via DataCite |
Submission history
From: Ruoyu Wang [view email]
[v1]
Wed, 29 Jul 2026 14:56:31 UTC (1,522 KB)
[v2]
Tue, 4 Aug 2026 11:03:49 UTC (1,594 KB)
[v3]
Tue, 11 Aug 2026 08:16:44 UTC (1,594 KB)
[v4]
Wed, 30 Sep 2026 13:52:55 UTC (1,594 KB)
[v5]
Sun, 1 Nov 2026 14:13:59 UTC (1,829 KB)
来源：arXiv cs.CL · arxiv.org