According to an article in the online American publication CSO , the providers of security solutions are relying more and more on artificial intelligence for detecting threats. These systems are still not perfect, but are already able to perceive threats considerably faster than humans. Teachable AI can analyze large quantities of data in a short amount of time and therefore recognize attacks in real time. Humans simply then have the task of combing out the false alarms and monitoring the quality of the data.
At the moment, AI systems are primarily used to recognize malware, phishing and brute force attacks. But the potential is much greater: artificial intelligence could, for example, filter out suspicious emails by analyzing variables such as the IP address, the sender’s location, the syntax and the word count. By monitoring the network traffic, an intelligent system can take down malware before it has inflicted any damage.
But criminal hackers are now also utilizing the advantages of AI. For example, they use teachable systems to detect weak areas in networks and use smart malware that recognizes when it’s being observed and makes itself invisible. CBR has already declared 2017 as " the year of smart malware ", due to AI malware that knows if it has landed in a sandbox environment or a honey pot and can even mutate on its own. The current paper on this topic has been written by Şerif Bahtijar: Anatomy of targeted attacks with smart malware .