A Threat Intelligence Event Extraction Conceptual Model for Cyber Threat Intelligence Feeds

Abstract

In response to the escalating cyber threats, the efficiency of Cyber Threat Intelligence (CTI) data collection has become paramount in ensuring robust cybersecurity. However, existing works encounter significant challenges in preprocessing large volumes of multilingual threat data, leading to inefficiencies in real-time threat analysis. This paper presents a systematic review of current techniques aimed at enhancing CTI data collection efficiency. Additionally, it proposes a conceptual model to further advance the effectiveness of threat intelligence feeds. Following the PRISMA guidelines, the review examines relevant studies from the Scopus database, highlighting the critical role of artificial intelligence (AI) and machine learning models in optimizing CTI data preprocessing. The findings underscore the importance of AI-driven methods, particularly supervised and unsupervised learning, in significantly improving the accuracy of threat detection and event extraction, thereby strengthening cybersecurity. Furthermore, the study identifies a gap in the existing research and introduces XBC conceptual model integrating XLM-RoBERTa, BiGRU, and CRF, specifically developed to address this gap. This paper contributes conceptually to the field by providing a detailed analysis of current CTI data collection techniques and introducing an innovative conceptual model to enhance future threat intelligence capabilities.