New algorithm could help predict future ISIS attacks
Fri 17 Jun 2016
Scientists have developed a new algorithm which may help law enforcement agencies predict potential terror attacks. The computer model has a particular focus on the behavioural patterns associated with Islamic State (IS) supporters.
The system is able to track and identify terrorist activities that may be able to help authorities prevent future ISIS attacks, according to the University of Miami research study. The algorithm was trained using second-by-second online footage of 196 ISIS groups shared over Europe’s largest social network site, VKontakte.
The researchers uncovered that while the majority of the 108,000+ group members had never met each other, they were still remarkably able to adapt and continue their online communications, increase their numbers and re-establish themselves after being closed down.
‘It was like watching crystals forming. We were able to see how people were materialising around certain social groups; they were discussing and sharing information – all in real-time,’ explained Neil Johnson, a physicist in the college of arts and sciences. ‘The question is: Can there be a signal of how people are coming collectively together to do something without a proper system in place?’
In the study, which was published in the journal Science yesterday, the team noted how they used a mathematical equation typically used in physics and chemistry to monitor the development and growth of pro-ISIS groups. They suggested that by tracking these groups and their operational communications, cybercrime police and other anti-terror groups could foil potential organised violence.
‘This removes the guess work. With that road map, law enforcement can better navigate what is going on, who is doing what, while state security agencies can better monitor what might be developing,’ said Johnson.
‘The message is: Find the aggregates – or at least a representative portion of them – and you have your hand on the pulse of the entire organisation, in a way that you never could if you were to sift through the millions of internet users and track specific individuals, or specific hashtags,’ he continued.