Dynamic Vulnerability Knowledge Graph Construction via Multi-Source Data Fusion and Large Language Model Reasoning

Authors:
Open Access
Publisher website
Google Scholar
Abstract
With the increasing number of network security threats and the frequent occurrence of software vulnerability attacks, the effective management and large-scale retrieval of vulnerability data have become urgent needs. Existing vulnerability information is scattered across heterogeneous sources and is difficult to integrate, which in turn makes it hard for security analysts to quickly retrieve and analyze relevant security knowledge. To address this problem, this paper proposes a method to construct a vulnerability knowledge graph by integrating multi-source vulnerability data, combining graph embedding technology with large language model reasoning to aggregate, infer, and enrich vulnerability knowledge. Experiments demonstrated that our domain-tuned Bidirectional Long Short-Term Memory–Conditional Random Field (BiLSTM-CRF) named entity recognition (NER), enhanced with a cybersecurity dictionary, achieved a 90.1% F1-score for entity extraction. For link prediction, a hybrid Graph Attention Network fused with GPT-3 reasoning boosted Hits1 by 0.137, Hits3 by 0.116, and Hits10 by 0.101 over the baseline. These results confirm that our approach markedly enhanced entity identification and relationship inference, yielding a more complete and dynamically updatable cybersecurity knowledge graph.
Funding Information
  • National Key Research and Development Program of China (2023YFE0111100, 62272370, 2022QNRC001, B16037, 2024QCY-KXJ-149, 241110210200, KLCS20240405, QTZX23071)
  • National Natural Science Foundation of China under Grant (2023YFE0111100, 62272370, 2022QNRC001, B16037, 2024QCY-KXJ-149, 241110210200, KLCS20240405, QTZX23071)
  • Young Elite Scientists Sponsorship Program by CAST (2023YFE0111100, 62272370, 2022QNRC001, B16037, 2024QCY-KXJ-149, 241110210200, KLCS20240405, QTZX23071)
  • the China 111Project (2023YFE0111100, 62272370, 2022QNRC001, B16037, 2024QCY-KXJ-149, 241110210200, KLCS20240405, QTZX23071)
  • Qinchuangyuan Scientist + Engineer Team Program of Shaanxi (2023YFE0111100, 62272370, 2022QNRC001, B16037, 2024QCY-KXJ-149, 241110210200, KLCS20240405, QTZX23071)
  • Songshan Laboratory (2023YFE0111100, 62272370, 2022QNRC001, B16037, 2024QCY-KXJ-149, 241110210200, KLCS20240405, QTZX23071)
  • Open Foundation of Key Laboratory of Cyberspace Security, Ministry of Education of China (2023YFE0111100, 62272370, 2022QNRC001, B16037, 2024QCY-KXJ-149, 241110210200, KLCS20240405, QTZX23071)
  • Fundamental Research Funds for the Central Universities (2023YFE0111100, 62272370, 2022QNRC001, B16037, 2024QCY-KXJ-149, 241110210200, KLCS20240405, QTZX23071)

This publication has 34 references indexed in Scilit: