A Cyber Threat Intelligence Model for Identification of Crime-Facilitating Elements on Darknet Marketplace Using Guided LDA-Based Topic Modeling Weights

DOI

10.2991/978-94-6239-610-4_7How to use a DOI?

Keywords

Darknet; Cyber Threat Intelligence; LDA Topic Modeling; NLP; Coherence Metrics; Machine Learning

Abstract

The dark web is a hidden part of the internet that provides anonymity and privacy to users by masking their identities through multiple layers of encryption. This structural nature enables it to function as a covert platform for various illicit activities. Recent data indicate that stolen and compromised personal information, as well as financial fraud, remain dominant forms of cybercrime. However, existing research mainly concentrates on identifying crime categories rather than uncovering the hidden background mechanisms that drive these high-impact cybercrimes. To address this gap, we propose a novel framework that employs Guided Latent Dirichlet Allocation (Guided LDA) technique to identify hidden activities behind stolen- financial data related crimes on darknet marketplaces. This study utilizes a publicly available dataset from Kilos, a darknet search engine that indexes information from six darknet markets. The findings reveal that the Guided LDA model produces coherent and meaningful topics across multiple coherence metrics (UMass, UCI, CNPMI, and CV), and effectively identifies the recurring activity patterns and key facilitating elements present in darknet communications. By using topic modeling, this study offers deeper insight into the ecosystem of darknet crimes, assisting researchers and law enforcement in better understanding the underlying dynamics and developing more effective cyber threat detection strategies.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Gowri Priya
AU  - S. Manohar Naik
PY  - 2026
DA  - 2026/05/05
TI  - A Cyber Threat Intelligence Model for Identification of Crime-Facilitating Elements on Darknet Marketplace Using Guided LDA-Based Topic Modeling Weights
BT  - Proceedings of the First International Conference on Advances in Forensics and Cyber Technologies (ICFACT 2025)
PB  - Atlantis Press
SP  - 42
EP  - 59
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6239-610-4_7
DO  - 10.2991/978-94-6239-610-4_7
ID  - Priya2026
ER  -