MIT researchers have developed a cybersecurity platform called AI2 that can detect 85 percent of attacks. It also reduces the number of “false positives” — nonthreats mistakenly identified as threats — by a factor of five. The system was tested on 3.6 billion pieces of data generated by millions of users over a period of three months. AI2 uses machine learning first to find the most important potential problems; only then it shows the top events to analysts for labeling. The more attacks the system detects, the more analyst feedback it receives, which in turn improves the accuracy of future predictions.”]
Source: https://www.csoonline.com/article/3058056/ai-humans-kick-ass-cybersecurity.html