MIT’s New AI Cybersecurity Platform Can Predict 85% of Cyber Threats

 

 

19 April 2016 :

The “AI2” algorithm was developed by the university’s Computer Science and Artificial Intelligence Lab (CSAIL)—in conjunction with machine learning startup PatternEx—and is reportedly three times better at detecting cyberattacks than other systems available today.

Predicting cyber attacks before they happen have two conventional approaches. One uses a set of indicators specified by an expert, and the other uses machines to detect abnormal activity. The problem with these approaches is that rules are often broken by criminals, and there is just too much abnormal activity flagged, even when these are not attacks

“You can think about the system as a virtual analyst,” says CSAIL research scientist Kalyan Veeramachaneni. “It continuously generates new models that it can refine in as little as a few hours, meaning it can improve its detection rates significantly and rapidly.”

AI2 is able to scan billions of log lines per day, assigning each piece of data as “normal” or “abnormal.” The more attacks that come in and the more feedback which is given by human operators, the better, as AI2 learns what to look out for.

“You can think about the system as a virtual analyst,” says CSAIL research scientist Kalyan Veeramachaneni, who developed AI2 with Ignacio Arnaldo, a chief data scientist at PatternEx and a former CSAIL postdoc. “It continuously generates new models that it can refine in as little as a few hours, meaning it can improve its detection rates significantly and rapidly.”
Veeramachaneni presented a paper about the system at last week’s IEEE International Conference on Big Data Security in New York City.

The team says that AI2 can scale to billions of log lines per day, transforming the pieces of data on a minute-by-minute basis into different “features”, or discrete types of behavior that are eventually deemed “normal” or “abnormal.”
“The more attacks the system detects, the more analyst feedback it receives, which, in turn, improves the accuracy of future predictions,” Veeramachaneni says. “That human-machine interaction creates a beautiful, cascading effect.”

 

Image : MIT

 

Send this to friend