Analysis tool would scan military e-mail for insider threats

A project funded through the Defense Advanced Research Projects Agency would identify the most serious insider threats to security by scanning all user e-mail messages, text messages, logins, file transfers and Web browsing on military networks, reports Katie Drummond at Wired’s Danger Room blog.

The two-year Proactive Discovery of Insider Threats Using Graph Analysis and Learning (PRODIGAL) project is being is being conducted by a consortium of five institutions led by Georgia Tech. The project falls under a larger initiative known as Anomaly Detection at Multiple Scales, which applies various technologies to scour through massive datasets.

By scanning an estimated 250 million e-mail messages, instant messages and file transfers daily, PRODIGAL might lead officials to a WikiLeaker before that person breaks the law. After the technology is ready, it will initially only be tested on government officials and military personnel who’ve agreed to be monitored, DARPA officials told the blog.

David A. Bader
David A. Bader
Distinguished Professor and Director of the Institute for Data Science

David A. Bader is a Distinguished Professor in the Department of Computer Science at New Jersey Institute of Technology.