Fight off cyber-attacks with AI and ML tech, says Ulster professor - The EE

Fight off cyber-attacks with AI and ML tech, says Ulster professor

Kevin Curran of Ulster University

With cyber-attacks increasing by 15% during the last six months of 2020 and 70% of financial sector firms suffering cyber-attacks in 2020, hackers have been on the rampage since the start of the pandemic.

As such, the ability to catch attacks in their early stages and mitigate any future risk has never been more important, says Kevin Curran, IEEE senior member and professor of cybersecurity at Ulster University.

Act now to mitigate attacks

The types of attacks and motivations of hackers can differ significantly, but the most effective ways for hackers to gain a foothold over devices is to install keyboard loggers or ransomware by getting people to simply click on infected links. With one in three people in the UK working exclusively at home, Prof. Curran argues that businesses must act now to mitigate attacks, by investing in advanced technology such as artificial intelligence (AI) and machine learning (ML) to help limit these types of cyber-attacks.

Curran comments, “AI is a buzzword impacting multiple industries, but it is especially critical in cybersecurity. Increasingly, organisations are faced with rising intrusion attacks, and it is becoming beyond the realm of humans to identify and isolate hacker packets on the network from legitimate connections.

Successful deployments

“Applying ML techniques can help to identify patterns and learn what is an attack. There are already successful examples and trials of AI being deployed with intrusion detection systems which can help with this. ML can also be used in the real world with helpful scenarios, such as detecting irregular financial transactions and customer profiling techniques, all which will aid with fraud detection methods, such as profiling anonymous patterns.

“AI and other interdisciplinary capabilities are increasingly being used to address the challenges of securing enterprises. ML can use statistics, AI, and pattern recognition to discover previously unknown, valid patterns and relationships in large data sets, which are useful for finding attacks and preserving privacy. We can never achieve perfect security in any system, but we can and we should attempt to mitigate risk where possible,” Curran concludes.

The author is Kevin Curran, IEEE senior member and professor of
cybersecurity at Ulster University

Follow us and Comment on Twitter @TheEE_io

By continuing to use the site, you agree to the use of cookies. more information

The cookie settings on this website are set to "allow cookies" to give you the best browsing experience possible. If you continue to use this website without changing your cookie settings or you click "Accept" below then you are consenting to this.