AI lie detector to question travellers entering EU

System will assess official documents, social media activity and biometric data - and analyse travellers' faces to see if they are lying

Samuel Osborne
Friday 02 November 2018 18:31 GMT
Comments
Four border crossings in Hungary, Greece and Latvia will test the system over six months
Four border crossings in Hungary, Greece and Latvia will test the system over six months (Matt Cardy/Getty Images)

A"smart lie-detection system" will question travellers seeking to enter the EU during a six-month trial in an attempt to identify illegal migrants.

Four border crossings in Hungary, Greece and Latvia will test the system, which will assess the official documents, social media activity and biometric data of those hoping to enter.

It will also ask travellers questions as they pass through the border checkpoint, such as “what is in your suitcase”, according to the New Scientist.

The AI will then reportedly analyse their faces as they give their answers, looking at 38 micro-gestures to spot facial patterns which some say are associated with lying.

Others disagree, however, with Bennett Kleinberg at the University of London telling the magazine the idea is controversial and has little evidence.

MPs approve European Union Withdrawl Bill

Those who pass the test will be given a QR code which, once scanned at the border, will let them through.

But those that are deemed to have lied will be referred to a human border official.

The trial of the tool, called iBorderCtrl, is being led by the Hungarian National Police.

In an early test on 30 people, half of which were told to lie, the tool identified the liars with around 76 per cent accuracy.

The team behind the system said they hoped to increase its accuracy by training it on a larger data set during the pilot.

Join our commenting forum

Join thought-provoking conversations, follow other Independent readers and see their replies

Comments

Thank you for registering

Please refresh the page or navigate to another page on the site to be automatically logged inPlease refresh your browser to be logged in