Title: A relational triplet extraction method for constructing network security knowledge graph

Authors: Guanlin Chen; Jiacong Xu; Tieming Chen; Wujian Yang; Wenyong Weng

Addresses: School of Computer and Computing Science, Hangzhou City University, Hangzhou, 310015, China; College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, 310014, China ' School of Computer and Computing Science, Hangzhou City University, Hangzhou, 310015, China; College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, 310014, China ' College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, 310014, China ' School of Computer and Computing Science, Hangzhou City University, Hangzhou, 310015, China ' School of Computer and Computing Science, Hangzhou City University, Hangzhou, 310015, China

Abstract: Faced with the challenges brought by the rapid growth of cyber threat intelligence (CTI) data, traditional information extraction methods have shown limitations regarding efficiency, accuracy, intelligence, and scalability. To help network security experts develop more solid security strategies based on reliable intelligence and improve network security defence and deterrence capability, this paper focuses on constructing a CTI knowledge graph based on a relational triplet. Besides, this paper provides a ternary extraction method for constructing a network security knowledge graph associated with a sensor system, which reduces the labour consumption of constructing a network security knowledge graph. Compared with the traditional method, the method is more efficient and accurate and can improve the performance of extracting entity relationships from complex text.

Keywords: network security; knowledge graph; sensor; named entity recognition; NER; relationship extraction.

DOI: 10.1504/IJSNET.2025.146122

International Journal of Sensor Networks, 2025 Vol.48 No.1, pp.44 - 53

Received: 09 Dec 2024
Accepted: 11 Dec 2024
Published online: 07 May 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article