Automated Analysis of Cybercriminal Markets

We have developed an automated, top-down approach for analyzing underground forums. Using natural language processing and machine learning, our approach can automatically generate high-level information about underground forums with high accuracy.

Read the paper


This is a collaborative study among researchers from the International Computer Science Institute, UC Berkeley, UC San Diego, and New York University.



Our code is available on github: It includes code for extracting information about the type of a post, products bought/sold, the prices of products, and currency exchanges.


We have used eight distinct forums to assess our tools: Antichat, Blackhat World, Carders, Darkode, Hack Forums, Hell, L33tCrew and Nulled.
  • Blackhat World (Dump): Contact authors
  • Nulled (Dump): Contact authors
  • Darkode (Scrape): Contact authors
  • Hack Forums (Scrape): Contact authors