Anomaly Detection at Multiple Scales

From Wikipedia, the free encyclopedia
Jump to: navigation, search
Anomaly Detection at Multiple Scales
Establishment 2011
Sponsor DARPA
Value $35 million
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.[1][2][3][4]

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 "a government employee [whom] abuses access privileges to share classified information".[2][5] Specific cases mentioned are Nidal Malik Hasan and Wikileaks alleged source Bradley Manning.[6] Commercial applications may include finance.[6] The intended recipients of the system output are operators in the counterintelligence agencies.[2][5]

The Proactive Discovery of Insider Threats Using Graph Analysis and Learning is part of the ADAMS project.[5][7] The Georgia Tech team includes noted high-performance computing researcher David A. Bader.[8]

See also[edit]


  1. ^ "ADAMS". DARPA Information Innovation Office. Retrieved 2011-12-05. 
  2. ^ a b c "Anomaly Detection at Multiple Scales (ADAMS) Broad Agency Announcement DARPA-BAA-11-04". General Services Administration. 2010-10-22. Retrieved 2011-12-05. 
  3. ^ Ackerman, Spencer (2010-10-11). "Darpa Starts Sleuthing Out Disloyal Troops". Wired. Retrieved 2011-12-06. 
  4. ^ Keyes, Charley (2010-10-27). "Military wants to scan communications to find internal threats". CNN. Retrieved 2011-12-06. 
  5. ^ a b c "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. 
  6. ^ a b "Video Interview: DARPA’s ADAMS Project Taps Big Data to Find the Breaking Bad". Inside HPC. 2011-11-29. Retrieved 2011-12-06. 
  7. ^ Brandon, John (2011-12-03). "Could the U.S. Government Start Reading Your Emails?". Fox News. Retrieved 2011-12-06. 
  8. ^ "Anomaly Detection at Multiple Scales". Georgia Tech College of Computing. Retrieved 2011-12-06.