Technology

AI in cybersecurity: A double-edged sword

AI is used to analyse data from millions of cyber incidents to identify potential threats. But it's is also being used by criminals to tweak their malicious tools.

14 February 2021

In the mid-1950s, John McCarthy coined the term ‘artificial intelligence’ as ‘the science and engineering of making intelligent machines’, says VMware SA’s lead technologist Ian Jansen van Rensburg. “Today, the words AI and machine learning (ML) are almost always used in the same sentence. AI is any technique that enables computers to mimic human behaviour. ML, on the other hand, takes a subset of AI techniques that use statistical methods to allow machines to improve with experience.”

AI and ML are two critical components when thinking about security, says Jansen van Rensburg. “The majority of today’s cyberattacks feature advanced tactics such as lateral movement and island-hopping. Attackers make use of intelligent methods and code to traverse a company’s security boundaries. These sophisticated hacking methods pose a tremendous risk to companies with decentralised systems protecting high-value assets, including money, intellectual property, and other sensitive information.”

ITWeb Premium

Get 3 months of unlimited access
No credit card. No obligation.

Already a subscriber Log in