How a computer program can prevent a terrorist attack


After a terrorist attack, the question always arises: Could this have been prevented?

The answer may lie at the intersection of data science and social science. A newly funded project among Colorado State University and Brandeis University researchers is aimed at creating a powerful, data-driven tool that can help law enforcement identify individuals headed toward violent extremism.

CSU’s Anura Jayasumana, professor of electrical and computer engineering with a joint appointment in computer science, and Brandeis’ Jytte Klausen have been awarded $731,000 over two years from the National Institute of Justice to develop a “dynamic risk assessment protocol” that can anticipate imminent risk of violence in individuals. The computational tool would monitor and screen for proven risk indicators of radicalization among large databases of people that would be impossible to comb through one by one.

“There is no protocol to identify, in real time, people getting radicalized,” Jayasumana said. “On top of that, law enforcement does not have the resources to look at millions of people. … Our purpose is to use the characteristics identified as radicalization indicators, and narrow down at-risk groups for law enforcement to look at.”

Jayasumana is a leader in network science, in addition to being an expert in data sciences related to pattern and anomaly detection. His expertise ranges from network mapping for IoT (Internet of Things) to communication among weather radars. He will lead the development of an algorithm that classifies data for the presence of radicalization indicators defined by Klausen’s team.

Western Jihadism Project

The project will build on the Western Jihadism Project that Klausen founded in 2006. The project includes a multimedia data archive that records the growth of Jihadism in Western Europe, North America and Australia since the early 1990s. It comprises records for terrorism offenders from 20 countries.

The Western Jihadism databases include material from personal social networks in Jihadist terrorist organizations and their recruitment efforts in Western nations. It contains information on 6,000 or more individuals, 797 plots that were successfully executed, failed or foiled, and local and international organizations linked to Western Jihadist extremists.

For the new partnership with CSU computer scientists, the Brandeis research team will continue its data collection methodology for subjects who commit acts of terror, but will include new data from 2015.

Helping law enforcement

Jayasumana said the work could help law enforcement intervene in some cases early, before the person or persons commit acts or become fully committed to violence.

Data scientists and social scientists cannot work alone in this case, Jayasuamana said. “You really need interaction between these two groups to tackle this,” he said. “[Social scientists] can do it on a small scale, and we can do learning and screening at a large scale, but we need to understand the problems and what to solve. These two groups coming together is important in that regard.”