Anomaly Detection at Multiple Scales
|Goal||Detect insider threats in defense and government networks|
Anomaly Detection at Multiple Scales, or ADAMS, is a $35 million DARPA project designed to identify patterns and anomalies in very large data sets. It is under DARPA's Information Innovation office and began in 2011.
The project is intended to detect and prevent insider threats such as "a soldier in good mental health becoming homicidal or suicidal", an "innocent insider becoming malicious", or "a government employee [whom] abuses access privileges to share classified information". Specific cases mentioned are Nidal Malik Hasan and Wikileaks alleged source Bradley Manning. Commercial applications may include finance. The intended recipients of the system output are operators in the counterintelligence agencies.
The Proactive Discovery of Insider Threats Using Graph Analysis and Learning is part of the ADAMS project. The Georgia Tech team includes noted high-performance computing researcher David A. Bader.
- "ADAMS". DARPA Information Innovation Office. Retrieved 2011-12-05.
- "Anomaly Detection at Multiple Scales (ADAMS) Broad Agency Announcement DARPA-BAA-11-04" (PDF). General Services Administration. 2010-10-22. Retrieved 2011-12-05.
- Ackerman, Spencer (2010-10-11). "Darpa Starts Sleuthing Out Disloyal Troops". Wired. Retrieved 2011-12-06.
- Keyes, Charley (2010-10-27). "Military wants to scan communications to find internal threats". CNN. Retrieved 2011-12-06.
- "Georgia Tech Helps to Develop System That Will Detect Insider Threats from Massive Data Sets". Georgia Institute of Technology. 2011-11-10. Retrieved 2011-12-06.
- "Video Interview: DARPA’s ADAMS Project Taps Big Data to Find the Breaking Bad". Inside HPC. 2011-11-29. Retrieved 2011-12-06.
- Brandon, John (2011-12-03). "Could the U.S. Government Start Reading Your Emails?". Fox News. Retrieved 2011-12-06.
- "Anomaly Detection at Multiple Scales". Georgia Tech College of Computing. Retrieved 2011-12-06.
|This military-related article is a stub. You can help Wikipedia by expanding it.|
|This software article is a stub. You can help Wikipedia by expanding it.|