|
|
 |
 |
August 2005 Fingerprint Math for Airport SecurityLast autumn Lawrence Wein detected serious shortcomings in a U.S. government program for identifying terrorists by checking visitors’ fingerprints at U.S. airports. Working with a Stanford graduate student, Wein determined that scanning eight or ten fingers instead of the current two could mean the screening processes would spot a significantly higher percentage of international travelers whose fingerprints identify them as suspected terrorists. Wein, the Business Schoool’s Paul E. Holden Professor of Management Science presented these findings to the White House, the U.S. Department of Homeland Security, two Congressional subcommittees, and published them in an academic journal. Under the US-VISIT program, which was developed as a result of the September 11, 2001, attacks on the World Trade Center and the Pentagon, most foreign citizens entering the United States have been required to have their fingerprints checked against those of known terrorists. U.S. Customs officials at airports lay each foreign visitor’s two index fingers down on a special pad and then wait while the computer compares the images against the fingerprints stored in the system of several million known criminals and suspected terrorists. When the computer detects a match, a person is quietly sequestered for further investigation. The system is 96 percent accurate overall, but when image quality is poor, accuracy drops to 53 percent, according to the mathematical models developed by Wein and Manas Baveja, a doctoral student at Stanford’s Institute for Computational and Mathematical Engineering and a science fellow at the university’s Center for International Security and Cooperation. “About 5 percent of the general public and 10 percent of those on the [government’s] watch list have bad quality fingerprints due either to genetics or hard labor,” Wein says. It’s those small percentages that can evade the system—with potentially huge consequences. “We assume that terrorist organizations will eventually defeat the US-VISIT program by employing a majority of people whose fingerprint quality is either naturally bad or deliberately made so,” he says. Wein and Baveja developed models that calculated how the system could be tweaked to improve accuracy without increasing either visitor waiting times at airports or the need for more customs staffing. “We found that instead of scanning two index fingers, scanning eight to ten fingers will result in a 95 percent detection probability, even when fingerprint quality is bad,” Wein says. In the meantime, Wein has proposed a short-term solution that will require only a minor software modification. “By loosening the detection thresholds on poor images you can catch more of these people,” he says. “You make up for the additional secondary inspection time this takes by slightly raising detection thresholds on good images.” Such an adjustment should raise the likelihood of catching suspects with the worst quality images from 53 to 73 percent. “There’s no excuse for a $10 billion program to settle for performance levels below 95 percent in all cases, and it’s my hope that the government will move quickly on this,” Wein says. While changing from a two-finger to an eight- or ten-finger system will necessitate expensive new hardware and major disruptions, he says the Department of Homeland Security realizes there is a serious vulnerability in its system and is currently assessing the best way to fix it. Earlier, Wein used mathematical modeling to determine that swift medical treatment, not prevention, is the most effective form of protection against anthrax attacks. That research also attracted the attention of government security agencies, and led to a program whereby the U.S. Postal Service will deliver antibiotics in the Washington, D.C., area in the event of a large anthrax attack. —MARGUERITE RIGOGLIOSO |
|
Further ReadingUsing Fingerprint Image Quality to Improve the Identification Performance of
the U.S. Visitor and Immigrant Status Indicator Technology Program
|
|
 |
|
|
|
Fingerprint Math for Airport Security
