研究人员开发了TACTIC-KG，一个旨在从非结构化网络威胁情报报告中构建网络安全知识图谱的新框架。与之前使用单一大型语言模型的方法不同，TACTIC-KG采用了一组专门的、轻量级的LLM代理来执行提取、类型化、验证和策展等任务。据报道，这种模块化方法与大型单一模型系统相比，提高了稳定性、召回率和图谱一致性，同时降低了成本并提高了性能。 AI
影响 这个代理框架可以提高构建网络安全知识图谱的效率和成本效益，可能有助于威胁情报的自动化分析。
排序理由 arXiv上发表的研究论文，详细介绍了构建知识图谱的新框架。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2607.05001v1 Announce Type: cross Abstract: Cyber Threat Intelligence (CTI) reports are predominantly unstructured, heterogeneous, and noisy, which limits their direct usability for automated analysis and reasoning. Cybersecurity Knowledge Graphs (CSKGs) provide a structure…
Cyber Threat Intelligence (CTI) reports are predominantly unstructured, heterogeneous, and noisy, which limits their direct usability for automated analysis and reasoning. Cybersecurity Knowledge Graphs (CSKGs) provide a structured representation of adversarial entities, actions,…
Cyber Threat Intelligence (CTI) reports are predominantly unstructured, heterogeneous, and noisy, which limits their direct usability for automated analysis and reasoning. Cybersecurity Knowledge Graphs (CSKGs) provide a structured representation of adversarial entities, actions,…