The kiosk that uses artificial intelligence to detect liars at airports

Translation of Wanda Thibodeaux’s article “This Artificial Intelligence Kiosk Is Designed to Spot Liars at Airports ” edited by www.inc.com

Alexa, cars that drive themselves, candidate selection processes. Artificial intelligence is fast becoming the norm in the business world. But it could also begin to play far more important roles in security, helping law enforcement and other security services detect malicious intruders. As Fredrick Kunkle of The Washington Post reports, there is now an artificial intelligence kiosk designed to detect whether travellers are in ‘unnatural agitation’ and potentially lying.

AVATAR

Designed by Aaron Elkins, professor at the Fowler College of Business Administration at San Diego State University, the new digital lie detector is called Automated Virtual Agent for Truth Assessments in Real Time, or AVATAR for short.

Once the ID or passport is scanned, the kiosk proceeds to subject the passenger to a very long series of questions. The questions cover common elements of everyday life or biographical information (when you were born, what your name is, your favourite food) as well as questions that could probe the person’s credibility (e.g. describe what you did today). Here is an example video:

If all goes well, the security staff should let the passenger go without any problems, but if the artificial intelligence programme detects behavioural abnormalities, the staff will detain the traveller for questioning or inspection.

How does artificial intelligence detect liars .

As a person answers AVATAR’s questions, the system uses certain sensors to collect non-verbal data emitted by the subject. More specifically, the system examines factors such as voice (tone, pronoun use, etc.), pupil dilation and eye movement, facial expressions and posture. The theoretical assumption behind the system is that the truthful person is less stressed (anxious) than the liar, as the liar spends a lot of mental and emotional energy trying to control himself. By analysing these involuntary behavioural elements, the system makes a judgement, although researchers are still studying these elements for scientific reliability. AVATAR is a big step forward compared to traditional polygraphs, which are unusable in highly populated environments and in doing this kind of analysis quickly on a large scale (e.g. the flow of visitors at an airport), and use more macroscopic physiological parameters (e.g. heart rate) that are generally not considered very reliable.

The

Future applications of AVATAR in the working world.

In theory, AVATAR could become widely used by local law enforcement agencies around the world, helping police to resolve a variety of conflicts. But its main intent is for security checks at borders and airports. These facilities are potentially at risk due to the high traffic of people that populate them every day, as well as possible threats from terrorism. Although these types of attacks can come from many different individuals or groups and can be local or foreign in nature, the increasing activity of the Islamic State of Iraq and Syria (ISIS) has been particularly alarming to leaders around the world. The attacks have led US President Donald Trump, for example, to call for a contrary embarkation ban on travellers from six Muslim-majority countries. AVATAR could one day help screen out individuals associated with ISIS or similar groups.

Right now, AVATAR is still in its ’embryonic’ stage of development: it only collects research data at border crossings in Mexico and Romania.
But, nevertheless, it is a beautiful demonstration of how science and technology can merge for the common good and public safety.