Victor Le Pochat (imec-DistriNet, KU Leuven), Tim Van hamme (imec-DistriNet, KU Leuven), Sourena Maroofi (Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG), Tom Van Goethem (imec-DistriNet, KU Leuven), Davy Preuveneers (imec-DistriNet, KU Leuven), Andrzej Duda (Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG), Wouter Joosen (imec-DistriNet, KU Leuven), Maciej Korczyński (Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG)
In 2016, law enforcement dismantled the infrastructure of the Avalanche bulletproof hosting service, the largest takedown of a cybercrime operation so far. The malware families supported by Avalanche use Domain Generation Algorithms (DGAs) to generate random domain names for controlling their botnets. The takedown proactively targets these presumably malicious domains; however, as coincidental collisions with legitimate domains are possible, investigators must first classify domains to prevent undesirable harm to website owners and botnet victims.
The constraints of this real-world takedown (proactive decisions without access to malware activity, no bulk patterns and no active connections to domains) mean that approaches from the state of the art cannot be applied. The problem of classifying thousands of registered DGA domain names therefore required an extensive, painstaking manual effort by law enforcement investigators. To significantly reduce this effort without compromising correctness, we develop a model that automates the classification. We achieve an accuracy of 95.8% on the ground truth of the 2017 Avalanche takedown, which translates into a reduction of up to 94.0% in manual investigation effort. Furthermore, we interpret the model to provide investigators with insights into how benign and malicious domains differ in behavior, which features and data sources are most important, and how the model can be configured according to the practical requirements of a real-world takedown.