If you’re thinking that Artificial Intelligence will lead to machines taking over the world, then you’ve overthought this concept a bit too much. Some people have thought about Artificial Intelligence as a fix for the world’s cybersecurity problems. So, is Artificial Intelligence the answer? In short, NO – Artificial Intelligence will not “solve” cyber security, nor does it imply adequate security. Artificial intelligence (AI, also machine intelligence, MI) is intelligence displayed by machines, in contrast with the natural intelligence (NI) displayed by humans and other animals.
The “pro” to AI, is that it speeds up processes and is intended to automate routine tasks, by taking away the element of human error. This can be very beneficial for log management, as an example, as it would be able to pick up incidents faster and more consistently across multiple data sources - more than a human would be capable of. As an example, a human can monitor logs, send alerts, create incidents, etc., for a couple of logs at a time, whereas AI could process infinite logs at an exponentially faster rate. The downfall to AI, however, is that it requires human intelligence to power it; it requires humans to input algorithms, set parameters, and set constraints.
Another example of using AI in cyber security could be on the wire with IDS/IPS and Firewalls. This means that before traffic can enter a network, it will be filtered through the firewalls and the IDS/IPS, where the AI will come into play by picking up known signatures and patterns of malware. AI will be very beneficial here as it constantly learns new signatures and would be able to pick up patterns or pieces of a signature faster than any other type of intelligence. Think of the Maps app on your smartphone; there is a feature enabled on most devices that tracks your frequent destinations, and later displays information about a frequented destination (i.e. travel time from your location to that destination). This function of tracking frequent occurrences will help AI pick up the patterns and signatures that are frequently found in malware.
According to Information Age: “Worldwide spending on AI systems is forecast to reach $12.5 Billion in 2017, and Gartner predicted that AI technologies would be used in almost every new software product by 2020”. Information Age continues to say: “While AI will enable [organizations] to begin automating some of the network security workload, enabling security teams to focus on strategic and threat reducing initiatives – [that will be its] limit.”
While AI can help rationalize normal network traffic, it will still need human input to make rational decisions about what is actually going on with the network and where security resources should be placed. AI could take on the menial tasks that slow security professionals down, and allow the experts to work out the “higher reasoning.” It World Canada, in its Top Cybersecurity Predictions for 2018, states: “In 2018, AI will not be the magic bullet. Instead we will see the growth of a more effective model which combines human touch with machine intelligence to reduce the number of false positives and improve time to detection.”
Want to improve your IT Security processes and save time? Click below for a demo of the Uzado platform.