Border securityBorder Patrol kiosk detects liars trying to enter U.S.

Published 21 August 2012

The U.S. Customs and Border Protection (CBP) is using border crossing stations in Arizona to test new technology to detect liars as they attempt to enter the country; travelers are subjected to a 5-minute interview with the kiosk, while microphones monitor vocal pitch frequency and quality, an infrared camera monitors eye movement and pupil dilation, and a high definition camera monitors facial expression

Demonstration of the AVATAR kiosk // Source: arizona.edu

The U.S. Customs and Border Protection (CBP) is using border crossing stations in Arizona to test new technology to detect liars as they attempt to enter the country.

The Automated Virtual Agent for Truth Assessments in Real-Time (AVATAR) kiosk interviews travelers while searching for signs of deception.

Doug Derrick, a member of the University of Arizona team developing the AVATAR thinks the kiosk will be a success.

What we’re looking for is changes in human physiology,” Derrick told CNN.  “We’ve had great success in reliably detecting these anomalies — things that people can’t really detect.”

Emergency Management reports that currently, the AVATAR is being tested at the Dennis DeConcini port in Nogales, Arizona on low-risk travelers who have been preapproved by human screeners as part of the CPB’s voluntary Trusted Traveler program. 

The travelers are subjected to a 5-minute interview with the kiosk, which displays an animated face that asks close-ended questions in English or Spanish and uses sensors to detect whether the person is lying. Microphones monitor vocal pitch frequency and quality, an infrared camera monitors eye movement and pupil dilation, and a high definition camera monitors facial expression.

People have a hard time detecting small changes in the frequency of the human voice, that a computer is much better at. People are accurate about 54 percent of the time at detecting deception. … We have got our machine as high as 90 percent in the lab,” Derrick said.

The results are sent to a human and in the case that the machine detects a lie; a more through interview will follow.

The animated face in the kiosk is named Elvis of Pat according to Derrick, and was given a face because officials discovered that travelers were not reposing to the question in a natural way.

EM notes that this is not the first time that lie detection machines are being used in security technology, but it is the first time it is being used to detect people coming into the country.

Artificial intelligence is being used for more than border security. After Enron, Bernie Madoff, and countless other financial scandals, artificial intelligence-based systems are now being developed to spot financial scams such as money laundering or insider trading, New Scientist reported.
Increasingly, police departments around the country are using crime-predicting software which analyzes data to identify high-crime areas where police departments should deploy their limited resources.