Although many of the headlines about AI alternate between the promise of self-driving cars and the coming doom of the AI overthrow of the job market, there is still a role for AI to play while everyone is on the same team. There can be no doubt, that with the modern state of computing horsepower available for AI applications, from data storage in the cloud to gaming circuits ideally suited to machine learning, AI can play a role in cyber security that would take hundreds of humans, thousands of hours, to fulfill.
While IBM’s Watson AI may be the modern face and friendly voice of artificial intelligence, multiple AI’s are operating behind the scenes inside the cyber security marketplace. According to a recent Nasdaq article “The amount of data generated from 200,000 daily cyber attacks result in humans wasting 20,000 hours annually chasing false positives. Not only is such a time allocation costly, but there simply is not enough human talent to execute a strictly “manned” cyber security response. The unemployment rate for cyber security analysts is 0.0% with 1 million positions remaining unfilled; artificial intelligence at first leverages, then supplements, and finally replaces human capital in various capacities. As previously alluded to, cyber security has literally exceeded the capabilities of humans.”
Ultimately, integration of AI into cyber security may rest in a hybridized approach. Here, human responses and artificial intelligence would respond together hopefully harvesting the best traits of each to mitigate threats. Researchers at MIT have created an AI algorithm called AI Squared that works with humans as it analyzes over 3.6 billion log files daily. Their tandem system can detect 85% of attacks while reducing false-positives 5-fold. As the machines learn, their performance is expected to improve.