If we discuss about toughest challenges of today’s business surely finding out cyber-attack and its mitigation will come at top of the list. Well it will take hours if we apply sniffing through entire date. In order to solve out the problem with ease, MIT is developing an AI which can easily works with human beings without getting tired for a moment.
The system developed by MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) is titled as AI2. The system has the potential to detect 86% percent attacks and able to scan about 3.6 billion log lines every day.
If you discuss about efficiency of the system it is far better and almost 3 times existing systems. The system continuously learns from human experts and will surely reduce the false positives by factor of 5.
According to experts the system able to cluster data in some meaningful patterns and will send the findings to human analysts who will be able identify actual attacks without any trouble.
In actual words the true story behind AI2 system is the perfect combination of artificial intelligence and analyst intuition.
You can also read here: How MIT develops perfect secure SMS system
Really interested to know about how MIT’s AI2 operates?
The system has been perfectly designed by two well known CSAIL research scientist Kalyan Veeramachaneni and Ignacio Arnaldo, at PatternEx.
According to Kalyan the system will continuously produce new models that will refine it in few little hours which means it can improve the detection rates rapidly and significantly.
Surely it will be highly interesting to see how the technology works in near future and able to provide us with better network security or not?