Have scientists discovered an algorithm that could thwart ISIS?

A team of University of Miami researchers may have found a way to use an existing mathematical equation to predict the next attack inspired by the Islamic State terrorist group.

A group of scientists may have discovered an existing mathematical equation that could help predict the next Islamic State-inspired terrorist attack.

While lone-wolf attacks, such as the one carried out by Omar Mateen in Orlando, Fla., are still difficult to stop, the new research suggests the most effective method of intelligence gathering on terrorist networks like the self-styled Islamic State militant group is to focus on the formation of small groups rather the activity of millions of individuals online users. Doing so could help predict when conditions are ripe for an attack, researchers say.

Scientists from the University of Miami, Fla., applied a mathematical model already used in physics and chemistry to examine the “ecology” of groups who support the Islamic State on Europe’s largest social media site, Vkontakte, from mid-2014 to August 2015. It showed how the roughly 108,000 individual members of pro-Islamic State groups were able to prolong their existence, increase rapidly in size, and inspire so-called lone wolves who never had previous terrorist inclinations, as happened in the Islamic State-inspired San Bernardino, Calif., attacks last year.

“It was like watching crystals forming. We were able to see how people were materializing around certain social groups; they were discussing and sharing information – all in real-time,” said physics professor Neil Johnson, who led the research, in a press release. “The question is: Can there be a signal of how people are coming collectively together to do something without a proper system in place?”

The the study, which suggests a certain order to the way such groups mushroom, was met with cautious optimism by terrorism experts. Many were grateful the researchers would share data with them, but said given how terrorist attacks are extremely difficult to predict and more research is still needed before any "code" is cracked.

“This is an interesting approach, this is a potentially valuable approach, and more research should be done on the approach,” said J. M. Berger, a fellow in George Washington University’s Program on Extremism and the co-author of “ISIS: The State of Terror,” told The New York Times. “But to jump ahead to the utility of it, I think, takes more work.”

The research, published Thursday in the journal Science, suggests an acceleration in the formation of online groups could signal a coming attack. This assertion was based on the Islamic State's unexpected 2014 attack on the Syrian town of Kobani that borders Turkey. Just before the Kobani offensive the number of pro-Islamic State, online groups grew sharply, Professor Johnson told the Times.

Johnson and his team say that by focusing on relatively small groups of the most hardcore Islamic State supporters who are discussing details about routes, financing, and avoiding drone strikes, cyber security and intelligence experts can get the most accurate picture of where a violent attack could erupt.

“So 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 organization, 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,” Johnson said in the release.

However, exactly how such information should be used is still unclear. As cyber security and other watchdogs have become quicker at shutting down such groups, the scientists watched how members were able to go dark before reincarnating in different forms.

“It’s virtually impossible to completely eradicate these guys from social networks,” George Washington University's Mr. Berger told News Hour. “But it is possible to inhibit the performance of a network. Propaganda doesn’t circulate, and it’s harder for them to recruit.

of 5 stories this month > Get unlimited stories
You've read 5 of 5 free stories

Only $1 for your first month.

Get unlimited Monitor journalism.