The Air Force is developing a data-mining technology meant to root out disaffected insiders based on their e-mail activity--or lack thereof, according to an article in this month's International Journal of Security and Networks.
The technology, based on something called Probabilistic Latent Semantic Indexing (PDF), scours an organization's e-mail traffic and constructs a graph of social network interactions illustrating employee activity. If a worker suddenly stops socializing online, abruptly shifts alliances within the organization, or starts developing an unhealthy interest in "sensitive topics," the system detects it and alerts investigators.
All part and parcel of the Military psychobiology techniques of of 'systems intelligence' vs 'Social intelligence' using an AI platform project to track the algorithm of social dissent.
Also, tangentially related, U.S. to Pay Millions to Spy on Gamers
U.S. Spies Want to Find Terrorists in World of Warcraft
By Ryan Singel February 22, 2008
Having eliminated all terrorism in the real world, the U.S. intelligence community is working to develop software that will detect violent extremists infiltrating World of Warcraft and other massive multiplayer games, according to a data-mining report from the Director of National Intelligence.
The Reynard project will begin by profiling online gaming behavior, then potentially move on to its ultimate goal of “automatically detecting suspicious behavior and actions in the virtual world.”
The cultural and behavioral norms of virtual worlds and gaming are generally unstudied. Therefore, Reynard will seek to identify the emerging social, behavioral and cultural norms in virtual worlds and gaming environments. The project would then apply the lessons learned to determine the feasibility of automatically detecting suspicious behavior and actions in the virtual world.
If it shows early promise, this small seedling effort may increase its scope to a full project.
Reynard will conduct unclassified research in a public virtual world environment. The research will use publicly available data and will begin with observational studies to establish baseline normative behaviors.
The publicly available report — which was mandated by Congress following earlier concerns over data-mining programs — also mentions several other data-mining initiatives. These include:
Video Analysis and Content Extraction – software to automatically identify faces, events and objects in video
Tangram – A system that wants to create surveillance and threat warning system that evaluates known threats and finds unknown threats to issue warnings ahead of an attack
Knowledge Discovery and Dissemination – This tool is reminiscent of the supposedly-defunct Total Information Awareness program. It seeks to access disparate databases to find patterns of known bad behavior. The program plans to work with domestic law enforcement and Homeland Security.
The report gives no indication why the find-a-terrorist cell in Sims project is called Reynard, though that is a traditional trickster figure in literature.