Northwestern University is set to unveil new reports from the Northwestern Terror Early Warning System (NTEWS), a machine-learning platform designed to forecast potential terrorist activities. The release is scheduled for Thursday, October 17, at the Conference on AI & National Security in Evanston, Illinois.
The event will commence with an introduction and demonstration of the system between 9 and 9:45 a.m. CDT. Hosted by the Northwestern Security and Artificial Intelligence Lab (NSAIL), the conference aims to explore how artificial intelligence can be integrated into national and global security strategies. It will feature presentations on emerging AI technologies and panel discussions with researchers and security strategists.
"The gradual drawdown of U.S. operations in Afghanistan and Iraq have led the world to a degree of complacency about terrorism," said V.S. Subrahmanian, who led NTEWS's development. He emphasized that threats persist globally from groups like Al-Shebaab, Boko Haram, Jama’at Nusrat al-Islam wal-Muslimin (JNIM), Lashkar-e-Taiba, and Abu Sayyaf.
Subrahmanian holds multiple roles at Northwestern as an AI expert, including Walter P. Murphy Professor of Computer Science at McCormick School of Engineering and director of NSAIL.
NTEWS focuses on predicting potential attacks by analyzing specific terrorist group activities. "NTEWS doesn’t predict attacks on specific locations or exact dates," explained Chiara Pulice, a senior researcher involved with NTEWS. However, it can estimate attack likelihoods over time frames ranging from one to six months for specific groups.
The platform uses publicly available data from news sources to model predictions initially developed for Boko Haram and Lashkar-e-Taiba. Now expanded, NTEWS includes models for Abu Sayyaf, Indian Mujahideen, Al-Shabaab, and JNIM. Starting Thursday, monthly reports will be released covering these six groups.
For media attendance at the event or report subscriptions, contact May Malone or fill out an online form.
May Malone contributed additional information to this report.