The case of accused Fort Hood shooter Maj. Nidal Hasan has contributed to effort to flag suspicious behavior ahead of time

The Pentagon wants computers to see into the future -- and stop crimes before they happen.
As the U.S Army considers whether Col. Nidal Hasan, the suspect in last year's Fort Hood massacre, should face a court-martial, it also is looking at whether the military missed signals that might have indicated what was about to happen.
Now a Pentagon research arm is asking scientists to create a way to scan billions of e-mails to identify suspects in advance so that crimes can be stopped before they are committed.
That's the goal of the latest $35 million project announced by DARPA, the Defense Advanced Research Projects Agency, which is credited with breakthroughs like the internet, GPS and stealth technology.
But this latest idea is already is drawing fire from privacy and security experts.
In a request for proposals, the think tank highlights the Fort Hood shootings.
"Each time we see an incident like a soldier in good mental health becoming homicidal or suicidal or an innocent insider becoming malicious, we wonder why we didn't see it coming," DARPA says. "When we look through the evidence after the fact, we often find a trail -- sometimes even an "obvious" one. The question is: Can we pick up the trail before the fact, giving us time to intervene and prevent an incident."
The agency calls the project ADAMS, for "Anomaly Detection at Multiple Scales."
Simply tracking messages to and from people around a single location like Fort Hood would be a vast task. There are 65,000 people at Fort Hood and in a single year they may create 4.68 billion electronic messages between almost 15 million people.
The challenge is to cope with and get accurate results from all this data.
The agency said it would primarily use ADAMS to look at "trusted person(s) in a secure environment with access to sensitive information and information systems and sources."
"There are currently no established techniques for detecting anomalies in data sets of this size at acceptable false positive rates," the agency notes in the request for proposals.
"The focus is on malevolent insiders that started out as 'good guys.' The specific goal of ADAMS is to detect anomalous behaviors before or shortly after they turn," the agency says. "Operators in the counterintelligence community are the target end-users for ADAMS insider threat detection technology."

Read More:http://edition.cnn.com/2010/US/10/27/pentagon.e.mail.profiling/index.html