"Using Machine Learning to Hunt Down Cybercriminals"

Researchers at MIT and the University of California at San Diego (UCSD) have developed a new machine-learning (ML) system that can be used to prevent IP hacking incidents before they occur by identifying serial IP hijackers. IP hijacking is a type of cyberattack in which cybercriminals exploit a flaw in the routing protocol for the Internet, Border Gateway Protocol (BGP). Through the performance of a BGP hijack, nearby networks can be convinced that a malicious actor's network has the best path to reach a specific IP address. The researchers gathered information from network operator mailing lists and historical BGP data to identify the common traits and behaviors of serial hijackers. Using the collected information, researchers trained their system to identify those traits and behaviors, allowing IP hacking incidents to be predicted in advance. This article continues to discuss the concept of IP hijacking, the ML system developed to detect such attacks before they occur, and the identification of false positives.

MIT News report "Using Machine Learning to Hunt Down Cybercriminals"