AI² - Better Prediction of Cyber-Attacks Using AI and Input from Human Experts

AI² – Better Prediction of Cyber Attacks Using Input from AI and Human Experts


These days, Artificial Intelligence (AI) is used more an more to help humanity with everyday tasks. Although AI is getting smarter and smarter every day, it seems that for better predication of cyber-attacks, a human input can still help significantly. In a new paper, researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and the machine-learning startup PatternEx demonstrate an artificial intelligence platform called AI² that predicts cyber-attacks significantly better than existing systems by continuously incorporating input from human experts

“The team showed that AI² can detect 85 percent of attacks, which is roughly three times better than previous benchmarks, while also reducing the number of false positives by a factor of 5…. To predict attacks, AI² combs through data and detects suspicious activity by clustering the data into meaningful patterns using unsupervised machine-learning. It then presents this activity to human analysts who confirm which events are actual attacks, and incorporates that feedback into its models for the next set of data.”

This short video below explains how it works –


Source: MIT