Darknet Data Mining -- A Canadian Cyber-crime Perspective
This work addresses cybercrime investigation challenges for Canadian law enforcement, but it is incremental as it applies existing data mining methods to new darknet data.
The paper tackled the problem of monitoring darknet marketplaces from a Canadian cybercrime perspective by developing a multi-stage data processing pipeline, resulting in findings such as a small Canadian presence and attribution of one cross-marketplace vendor through data visualization.
Exploring the darknet can be a daunting task; this paper explores the application of data mining the darknet within a Canadian cybercrime perspective. Measuring activity through marketplace analysis and vendor attribution has proven difficult in the past. Observing different aspects of the darknet and implementing methods of monitoring and collecting data in the hopes of connecting contributions to the darknet marketplaces to and from Canada. The significant findings include a small Canadian presence, measured the product categories, and attribution of one cross-marketplace vendor through data visualization. The results were made possible through a multi-stage processing pipeline, including data crawling, scraping, and parsing. The primary future works include enhancing the pipeline to include other media, such as web forums, chatrooms, and emails. Applying machine learning models like natural language processing or sentiment analysis could prove beneficial during investigations.