Most accurate lie detection to date from ‘tell-tale’ muscle activation claimed

A new technology analyzes tell-tale activation of facial muscles to reveal the telling of a lie with unprecedented 73 percent accuracy, via a technique developed at Tel Aviv University, as a campaigner files lawsuit against the EU for alleged secret research to trial video lie detectors on travelers arriving at its borders.

The peer-reviewed study published in Brain and Behavior found there are two types of ‘liars’ – those who activate specific cheek muscles when they lie and those who activate their eyebrows. Researchers believe the facial analysis technology has great potential for real-life contexts such as security and crime.

The process used stickers containing electrodes and printed onto soft surfaces. They measure the electrical activity of muscles and nerves, a process known as facial surface electromyography (sEMG), but now boosted by far more powerful sensors. The stickers are already commercially available and in use for sleep monitoring and neurological disease monitoring.

“Many studies have shown that it’s almost impossible for us to tell when someone is lying to us. Even experts, such as police interrogators, do only a little better than the rest of us,” Professor Dino Levy from the Coller School of Management and part of the research team told Eureka Alert.

“Existing lie detectors are so unreliable that their results are not admissible as evidence in courts of law – because just about anyone can learn how to control their pulse and deceive the machine. Consequently, there is a great need for a more accurate deception-identifying technology. Our study is based on the assumption that facial muscles contort when we lie, and that so far no electrodes have been sensitive enough to measure these contortions.”

By using machine learning the team was able to detect which muscles were activated when the subject was telling a simple lie.

The researchers believe that in the future the electrodes may become redundant if video software were able to detect the facial muscle movements.

“In the bank, in police interrogations, at the airport, or in online job interviews, high-resolution cameras trained to identify movements of facial muscles will be able to tell truthful statements from lies,” Levy is quoted as saying.

“Right now, our team’s task is to complete the experimental stage, train our algorithms and do away with the electrodes. Once the technology has been perfected, we expect it to have numerous, highly diverse applications.”

In the EU, video-based lie detection technology has already been put to use in one such setting: border crossings. Anti-surveillance campaigner and Member of the European Parliament, Dr. Patrick Breyer of the Pirate Party, has announced Friday that his transparency lawsuit against “secret EU surveillance research” should receive its judgement from the European Court of Justice on 15 December in Luxembourg, 33 months after he filed a lawsuit for the release of secret documents on the ethical justifiability, legality and results.

Breyer believes the ruling could shed light on EU-funded “security research” more generally. “In April 2021, it emerged that the ‘iBorderCtrl’ project, which was entirely funded by the EU, used part of its funding to lobby legislators for fundamental rights restrictions which would allow the use of its controversial technology on travellers,” writes Breyer in a statement on the result date.

“The EU Commission tried to hide this in a partially redacted document that was reconstructed by technical means. In her response to a written question by Patrick Breyer, EU Commissioner for Home Affairs Ylva Johansson denied that the lobbying— which was clearly proven in the document— had taken place. In October, the European Parliament expressed ‘concern’ about the iBorderCtrl project. Under a follow-up project, ‘Tresspass,’ the EU has again funded the testing of unscientific technology to ‘assess the sincerity of the traveller and his statements.’”

Article Topics

accuracy  |  biometrics  |  biometrics research  |  criminal ID  |  facial analysis  |  iBorderCtrl  |  lie detection  |  machine learning  |  video analytics