English(EN) Staying on the Attack Path: Structured State for Long-Horizon Automated Penetration Testing

新型智能代理Intentest使用DAG改进自动化网络安全渗透测试

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-10 04:00

研究人员开发了Intentest，这是一种新颖的智能代理，专为网络安全中的长周期自动化渗透测试而设计。该代理通过将状态外部化到持久的事实-意图有向无环图（DAG）上，解决了基于LLM的系统中的上下文遗忘和意图漂移问题。Intentest将已验证的网络状态存储为事实节点，并将探索方向存储为意图边，显著减少了无效转换并提高了探索效率。在真实的Capture the Flag挑战中进行评估，Intentest取得了88.2%的总体成功率，与基线方法相比有了显著提高，尤其是在更难的任务上。 AI

影响增强了LLM在复杂、长周期的网络安全任务中的能力，可能改进自动化漏洞发现。

排序理由学术论文，详细介绍了一种使用LLM和DAG进行自动化渗透测试的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了一种使用LLM和DAG进行自动化渗透测试的新方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Weizhe Wang, Yitong Zhang, Yao Zhang, Xiaoqiang Di, Zhigang Li, Bin Wu, Guangquan Xu · 2026-09-10 04:00

保持攻击路径：面向长周期自动化渗透测试的结构化状态

arXiv:2609.07344v1 Announce Type: cross Abstract: Large language model (LLM) based agents are increasingly applied to cybersecurity tasks such as vulnerability discovery and automated penetration testing. On long-horizon security tasks, however, such agents remain limited by cont…

本文如何被排名

报道来源 [1]

保持攻击路径：面向长周期自动化渗透测试的结构化状态

相关实体

相关话题