AI Detects Cyber-attacks with Accuracy after Attending MIT

MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) has announced AI Squared (AI²) – an artificial intelligence project said to detect cyber-attacks with an astonishing 86 percent accuracy. This breakthrough in cyber threat detection promises to “dramatically lower the amount of time human analysts spend sorting through information in search of evidence of cyber-attacks” through teaching AI² to “better identify and filter out false positives over time which are a big cause of wasted man-hours.” Instead of relying on humans to spend vast amounts of time sorting through false positives and actual signs of an attack, AI² has the ability to continuously generate new models and refine them in just hours, benefiting only from limited human input. Additionally, over time AI² will “send less and less false positives to human analysts to review, leaving them more and more time to evaluate and resolve actual threats.” In the end, this development could potentially improve the detection of false positives five-fold with a three-fold improvement regarding detection capabilities.