Artificial intelligence used to detect abusive domain names when registered

Researchers at Princeton University and the University of California have developed a technique based on artificial intelligence that can determine the reputation of a domain name at the time of domain registration. The technique, called PREDATOR (Proactive Recognition and Elimination of Domain Abuse at Time-Of-Registration) is based on a machine-learning algorithm, and it is said to be able to accurately and automatically identify malicious domain names at the time of registration. PREDATOR has been designed based on the assumption that criminals need to obtain many domains to ensure profitability and attack agility, leading to abnormal registration behaviours. The technique was evaluated using registration logs of domain names under .com and .net  over five months and was found to achieve 70% detection rate with a false positive rate of 0.35%.