Digital border guards with an AI LIE DETECTOR will interrogate travellers over what is in their suitcase at EU borders in a bid to toughen security

• iBorderCtrl will quiz travellers at four crossings in Hungary, Latvia, and Greece
• It uses AI to scan your face while you answer questions about your travels
• The system is part of a six-month trial run by the Hungarian National Police 

A digital border guard will interrogate travellers at some European Union borders in an attempt to ramp up security at crossings. Dubbed iBorderCtrl, the agent features an AI lie detector that quizzes tourists on their trip, including the contents of their suitcase (Mailonline stock)

By Harry Pettit for Mailonline; Published: 1 November 2018

A digital border guard will interrogate travellers at some European Union borders in an attempt to ramp up security at crossings.

Dubbed iBorderCtrl, the agent features an AI lie detector that quizzes tourists on their trip, including the contents of their suitcase.

The system is part of a six-month trial run by the Hungarian National Police at four different border crossing points in Hungary, Latvia, and Greece.

Each crossing borders a country outside of the EU.

If successful, the technology could be rolled out to borders across the union's member states.

'We're employing existing and proven technologies - as well as novel ones - to empower border agents to increase the accuracy and efficiency of border checks,' project coordinator George Boultadakis of European Dynamics in Luxembourg.

'iBorderCtrl's system will collect data that will move beyond biometrics and on to biomarkers of deceit.'

The digital border guard will question people after they have passed through a checkpoint.

It works via your laptop or phone, using your device's camera to record your face when you give answers.

The system then uses AI software to scan the video for 38 'micro-gestures' which it scores to assess whether a traveller is lying.

Questions include, 'What's in your suitcase?' and 'If you open the suitcase and show me what is inside, will it confirm your answers were true?', New Scientist reports.

Those that pass the test will receive a QR code that they can scan to cross the border.

If a traveller doesn't pass the test, the AI will reportedly take a more serious tone, and hand the offender to a human border agent for further questioning.

During the upcoming pilot, iBorderCtrl will quiz real tourists, though it won't affect their ability to travel.

Travellers will be invited to take part in the trial after they have passed through one of the four test crossings.

An early version of the system was tested using 30 volunteers at a fake border crossing.

The system is part of a six-month trial run by the Hungarian National Police at four different border crossing points in Hungary, Latvia, and Greece. Each crossing borders a country outside of the EU (Mailonline stock)

Half were told to lie to the bot, while the other half told the truth. The AI guessed correctly with an accuracy rate of 76 per cent.

Experts said the AI's accuracy rate in the real world could be lower, as people who are told to lie present clearer facial tells than those who fib earnestly.

'If you ask people to lie, they will do it differently and show very different behavioural cues than if they truly lie, knowing that they may go to jail or face serious consequences if caught,' Maja Pantic, a Professor of Affective and Behavioral Computing at Imperial College London, told New Scientist.

'This is a known problem in psychology.' 

With more than 700 million people travel through the EU every year, according to the European Commission, the low hit rate raises concerns over the number of travellers who could get away with lying at the border.

iBorderCtrl team Keeley Crockett, a researcher at Manchester Metropolitan University, said they are 'hopeful' they can bring the accuracy rate up to 85 per cent.

AI systems rely on artificial neural networks (ANNs), which try to simulate the way the brain works in order to learn.

ANNs can be trained to recognise patterns in information - including speech, text data, or visual images - and are the basis for a large number of the developments in AI over recent years.

Conventional AI uses the input to 'teach' an algorithm about a particular subject by feeding it massive amounts of information.

AI systems rely on artificial neural networks (ANNs), which try to simulate the way the brain works in order to learn. ANNs can be trained to recognise patterns in information - including speech, text data, or visual images (Mailonline)

Practical applications include Google's language translation services, Facebook's facial recognition software and Snapchat's image altering live filters.

The process of inputting this data can be extremely time consuming and is limited to one type of knowledge.

A new breed of ANNs called Adversarial Neural Networks pits the wits of two AI bots against each other, which allows them to learn from each other.

This approach is designed to speed up the process of learning, as well as refining the output created by AI systems.

- Further reading: An AI lie detector will interrogate travellers at some EU borders | New Scientist

- Mailonline
- https://www.dailymail.co.uk/sciencetech/article-6341801/AI-lie-detector-interrogate-travellers-EU-borders.html