Researchers at the University of Texas have developed a cybersecurity defence approach to fool hackers into revealing their secrets.

Their DEEP-Dig, or DEcEPtion DIGging, technique uses a decoy website to lure hackers into revealing their tactics. Artificial intelligence (AI) then records the activity of the hacker and carries out an analysis of the data to provide clues designed to teach it how to fend off future attacks.

The technique is a form of cybersecurity called ‘deception technology’, which involved setting traps for hackers and learning from their movements. The hope is that the technology could be used to protect defence organisations in the future.

Dr Kevin Hamlen, professor of computer science at The University of Texas, said: “There are criminals trying to attack our networks all the time, and normally we view that as a negative thing.

“Instead of blocking them, maybe what we could be doing is viewing these attackers as a source of free labour. They’re providing us data about what malicious attacks look like. It’s a free source of highly prized data.”

Recommended

• CodeBase Launches Digital Festival to Inspire Young Scots
• Edinburgh Tech Aims to Eliminate WiFi Notspots on Trains
• Steven Seagal Hit With £240,000 Fine for Cryptocurrency Promotion Scheme

Hackers tend to start with their simplest tricks but start using more sophisticated attacks as they gain confidence. The data collected could help to identify hacks at any stage of this process, helping to solve the challenges of using AI for cybersecurity, such as being mainly restricted to the understanding of user inputs, user behaviour, and user interactions.

Dr Gbadebo Ayoade, who presented the scientists’ findings in Puerto Rico and Hawaii, said that having more data will make it easier to detect when an attack is underway.

He added: “We’re using the data from hackers to train the machine to identify an attack. We’re using deception to get better data.”

Applications such as this could help to develop the future of AI for cybersecurity, which is becoming more popular as attacks become more sophisticated.