Journal
COMPUTERS & SECURITY
Volume 132, Issue -, Pages -Publisher
ELSEVIER ADVANCED TECHNOLOGY
DOI: 10.1016/j.cose.2023.103371
Keywords
Threat intelligence; Knowledge graph; Relation extraction; Joint model; Knowledge fusion
Categories
Ask authors/readers for more resources
With the emergence of various new attack techniques, cyber-attacks have become increasingly sophisticated and difficult to handle, posing significant threats to companies and individuals. Therefore, it is crucial to analyze attack incidents and trace the responsible attack groups. This paper proposes a threat intelligence framework that extracts, correlates, and unifies cybersecurity entity-relation triples from structured and unstructured data using a Cybersecurity Knowledge Graph (CKG).
Cyber-attacks, with various emerging attack techniques, are becoming increasingly sophisticated and dif-ficult to deal with, posing great threats to companies and every individual. Therefore, analyzing attack incidents and tracing the attack groups behind them becomes extremely important. Threat intelligence provides a new technical solution for attack traceability by constructing Cybersecurity Knowledge Graph (CKG). In this paper, we propose a framework for threat intelligence extraction and fusion, which is able to extract, correlate and unify cybersecurity entity-relation triples from structured and unstructured data. However, the existing entity and relation extraction for cybersecurity concepts uses the traditional pipeline model that suffers from error propagation and ignores the connection between the two subtasks. To solve the above problem, we propose a joint entity and relation extraction model for cybersecurity concepts. We model the joint extraction problem as a multiple sequence labeling problem, generating separate label sequences for different relations, which contain information about the involved entities and the subject and object of that relation. Experimental results on Open Source Intelligence (OSINT) data show that the F1 value of the joint model is 81.37%, which is better than the previous pipeline model. For the knowledge fusion, we propose an improved Levenshtein distance to correlate the same entities extracted from different data sources to construct a preliminary CKG, which is demonstrated in the Experiments section.& COPY; 2023 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available