Transformer-Based Threat Intelligence Frameworks Using BERT and GPT for Dark Web Analysis and Cybercrime Prediction
R Boopathi, Indumathi Venkatesan, J. Briskilal · 2025
The increasing sophistication of cyber threats originating from the Dark Web has necessitated the development of advanced threat intelligence frameworks capable of detecting and predicting malicious activities in real time. Traditional cybersecurity approaches often struggle to process the vast, unstructured, and linguistically diverse data generated on underground forums and illicit marketplaces. Transformer-based natural language processing (NLP) models, such as Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-trained Transformers (GPT), have demonstrated exceptional capabilities in understanding and generating contextualized textual representations, making them highly effective for Dark Web analysis and cybercrime prediction. This chapter explores the integration of transformer-based models in cyber threat intelligence workflows, emphasizing their ability to automate the identification of emerging threats, detect cybercriminal activities, and forecast evolving attack patterns. Key challenges, including data scarcity, adversarial linguistic variations, and ethical considerations in Dark Web monitoring, are analyzed alongside potential solutions leveraging AI-driven methodologies. , the chapter discusses the implications of transformer-based threat intelligence frameworks for real-time cybersecurity applications and future research directions aimed at enhancing cyber resilience. The insights presented contribute to the advancement of AI-driven cyber threat intelligence, enabling proactive threat mitigation strategies in an increasingly complex digital threat landscape.