PipCKG-BS: A Method to Build Cybersecurity Knowledge Graph for Blockchain Systems via the Pipeline Approach

Abstract

The increasing sophistication of cyberattacks on blockchain systems has significantly disrupted security experts from gaining immediate insight into the security situation. The Cybersecurity Knowledge Graph (CKG) currently provides a novel technical solution for blockchain system situational awareness by integrating massive fragmented Cyber Threat Intelligence (CTI) about blockchain technology. However, the existing literature does not provide a solution for building CKG appropriate for blockchain systems. Therefore, designing a method to construct a CKG for blockchain systems by efficiently extracting information from the CTI is mandatory. This paper proposes PipCKG-BS, a pipeline-based approach that builds CKG for blockchain systems. The PipCKG-BS incorporates contextual features and Pre-trained Language Models (PLMs) to improve the performance of the information extraction process. Precisely, we develop the Named Entity Recognition (NER) and Relation Extraction (RE) models for cybersecurity text in PipCKG-BS. In the NER model, we apply the prompt-based learning paradigm to cybersecurity text by constructing prompt templates. In the RE model, we employ external features and prior knowledge of sentences to improve entity relationship extraction accuracy. Several experimental results demonstrate that PipCKG-BS is better than advanced methods in extracting CTI information and is an appealing solution to build high-quality CKG for blockchain systems.