arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.02528cs.CRcs.AIcs.CL
收藏

利用知识图谱与大语言模型实现可操作的网络威胁情报

Actionable Cyber Threat Intelligence using Knowledge Graphs and Large Language Models

Mittweida University of Applied Sciences(米特韦达应用科学大学);Rochester Institute of Technology(罗切斯特理工学院)

Romy Fieblinger, Md Tanvirul Alam, Nidhi Rastogi

AI总结:

本文研究利用开源大语言模型与知识图谱从非结构化网络威胁情报中自动提取可操作信息,通过提示工程、guidance框架和微调优化三元组提取并构建可查询知识图谱,实验表明guidance与微调优于提示工程,但大规模应用仍面临挑战。

摘要:

网络威胁持续演变。从非结构化的网络威胁情报(CTI)数据中提取可操作的见解,对于指导网络安全决策至关重要。微软、趋势科技和CrowdStrike等组织越来越多地使用生成式人工智能来促进CTI提取。本文针对利用大语言模型(LLMs)和知识图谱(KGs)的进展来自动化提取可操作CTI的挑战展开研究。我们探索了最先进的开源LLMs的应用,包括Llama 2系列、Mistral 7B Instruct和Zephyr,用于从CTI文本中提取有意义的三元组。我们的方法评估了提示工程、guidance框架和微调等技术,以优化信息提取和结构化。提取的数据随后被用于构建知识图谱,提供威胁情报的结构化且可查询的表示。实验结果证明了我们的方法在提取相关信息方面的有效性,其中guidance和微调表现出优于提示工程的性能。然而,尽管我们的方法在小规模测试中被证明有效,但将LLMs应用于大规模数据以进行知识图谱构建和链接预测仍面临持续挑战。

英文摘要:

Cyber threats are constantly evolving. Extracting actionable insights from unstructured Cyber Threat Intelligence (CTI) data is essential to guide cybersecurity decisions. Increasingly, organizations like Microsoft, Trend Micro, and CrowdStrike are using generative AI to facilitate CTI extraction. This paper addresses the challenge of automating the extraction of actionable CTI using advancements in Large Language Models (LLMs) and Knowledge Graphs (KGs). We explore the application of state-of-the-art open-source LLMs, including the Llama 2 series, Mistral 7B Instruct, and Zephyr for extracting meaningful triples from CTI texts. Our methodology evaluates techniques such as prompt engineering, the guidance framework, and fine-tuning to optimize information extraction and structuring. The extracted data is then utilized to construct a KG, offering a structured and queryable representation of threat intelligence. Experimental results demonstrate the effectiveness of our approach in extracting relevant information, with guidance and fine-tuning showing superior performance over prompt engineering. However, while our methods prove effective in small-scale tests, applying LLMs to large-scale data for KG construction and Link Prediction presents ongoing challenges.

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。

↑