Several European airports will deploy an AI-powered lie detector at border checkpoints in a trial run of the new technology, reports CNN.
When a passenger approaches customs, they will be asked a series of questions by a "virtual border guard avatar," which will use an Artificial Intelligence to monitor their faces to quickly determine whether they are lying in an effort to reduce congestion.
The avatar will become "more skeptical" and change its tone of voice if it believes a person has lied, before referring suspect passengers to a human guard and allowing those believed to be honest to pass through, said Keeley Crockett of Manchester Metropolitan University in England, who was involved in the project.
"It will ask the person to confirm their name, age and date of birth, (and) it will ask them things like what the purpose of their trip is and who is funding the trip," said Crockett. -CNN
The project comes at an initial cost of $5.1 million (€4.5 million), and will begin its trial run at airports in Grece, Latvia and Hungary for passengers traveling outside the EU.
The technology has only been tested on a scant 32 individuals thus far, however the scientists behind the AI hope to achieve an 85% success rate. Prior facial recognition algorithms have been shown to have higher error rates with women and darker-skinned people after an MIT study earlier this year found bias in similar technology developed by Microsoft and IBM.