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 2405.04753cs.CRcs.AI
收藏

AttacKG+:利用大型语言模型增强攻击知识图谱构建

AttacKG+:Boosting Attack Knowledge Graph Construction with Large Language Models

College of Electronic Engineering, National University of Defense Technology(国防科技大学电子工程学院);University of Science and Technology of China(中国科学技术大学);National University of Singapore(新加坡国立大学)

Yongheng Zhang, Tingwen Du, Yunshan Ma, Xiang Wang, Yi Xie, Guozheng Yang, Yuliang Lu, Ee-Chien Chang

AI总结:

本文提出基于LLM的全自动框架AttacKG+,通过四模块提示与上下文学习及升级模式,从CTI报告中构建多层时序攻击知识图谱。

摘要:

攻击知识图谱构建旨在将文本形式的网络威胁情报(CTI)报告转换为结构化表示,以刻画网络攻击的演化轨迹。尽管已有研究提出了多种构建攻击知识图谱的方法,但这些方法通常存在两方面不足:对多样化知识类型的泛化能力有限,并且需要模型设计与调优方面的专业知识。针对这些局限,本文尝试利用大型语言模型(LLM);凭借出色的语言理解能力和零样本任务执行能力,LLM已在广泛任务中取得巨大成功。因此,我们提出一种基于LLM的全自动攻击知识图谱构建框架,名为AttacKG+。该框架包含四个连续模块:rewriter、parser、identifier和summarizer,每个模块均通过LLM支持的指令提示和上下文学习实现。此外,我们升级了现有攻击知识模式,提出一个更全面的版本。我们将网络攻击表示为随时间展开的事件,其每个时间步骤封装三层表示,包括行为图、MITRE TTP标签和状态摘要。大量评估表明:1)我们的形式化设计能够无缝满足威胁事件分析中的信息需求;2)该构建框架能够有效、忠实且准确地抽取AttacKG+所定义的信息;3)我们的攻击图可直接惠及攻击重建等下游安全实践。所有代码和数据集将在论文被接收后发布。

英文摘要:

Attack knowledge graph construction seeks to convert textual cyber threat intelligence (CTI) reports into structured representations, portraying the evolutionary traces of cyber attacks. Even though previous research has proposed various methods to construct attack knowledge graphs, they generally suffer from limited generalization capability to diverse knowledge types as well as requirement of expertise in model design and tuning. Addressing these limitations, we seek to utilize Large Language Models (LLMs), which have achieved enormous success in a broad range of tasks given exceptional capabilities in both language understanding and zero-shot task fulfillment. Thus, we propose a fully automatic LLM-based framework to construct attack knowledge graphs named: AttacKG+. Our framework consists of four consecutive modules: rewriter, parser, identifier, and summarizer, each of which is implemented by instruction prompting and in-context learning empowered by LLMs. Furthermore, we upgrade the existing attack knowledge schema and propose a comprehensive version. We represent a cyber attack as a temporally unfolding event, each temporal step of which encapsulates three layers of representation, including behavior graph, MITRE TTP labels, and state summary. Extensive evaluation demonstrates that: 1) our formulation seamlessly satisfies the information needs in threat event analysis, 2) our construction framework is effective in faithfully and accurately extracting the information defined by AttacKG+, and 3) our attack graph directly benefits downstream security practices such as attack reconstruction. All the code and datasets will be released upon acceptance.

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。

↑