Deliu, Isuf, Carl Leichter, and Katrin Franke. "Collecting cyber threat intelligence from hacker forums via a two-stage, hybrid process using support vector machines and latent dirichlet allocation." 2018 IEEE International Conference on Big Data (Big Data). IEEE, 2018.

Traditional security measures like firewalls and anti-virus software often struggle to keep up with evolving cyber threats. Cyber Threat Intelligence (CTI) from unconventional sources, such as hacker forums and dark-web platforms, can offer valuable insights. However, manual analysis of these sources is time-consuming and error-prone. This paper presents a hybrid Machine Learning model combining Support Vector Machines for post identification and Latent Dirichlet Allocation for clustering. Tested on data from a hacker forum, the model efficiently extracts relevant threat information, such as leaked credentials and malware, demonstrating its utility in enhancing traditional security measures.