Tel Aviv University Professor Yael Hanein. Photo: Tel Aviv University

Israeli scientists have developed a high-sensitivity method to measure the movement of facial muscles, able to uncover lies with a 73 percent accuracy, according to the findings of an initial research study.

The study, led by Professor Yael Hanein of Tel Aviv University’s Center of Nanoscience and School of Electrical Engineering and Professor Dino Levy from the Coller School of Management, is based on the assumption that facial muscles contort when individuals are not telling the truth.

The scientists identified two different groups of “liars” among the participants of the study: those who use their cheek muscles when they lie, and those who activate their eyebrows. The researchers believe that the technology can be used for developing video software and high-resolution cameras to make a better lie detector.

“Many studies have shown that it is 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,” said Levy. “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,” Prof. Levy added.

For the initial study, researchers attached locally-developed wireless sticker electrodes to the trial participants’ cheek muscles, close to the lips, and the muscles over the eyebrows to record electrical activity. They then applied machine-learning algorithms to detect lies based on brief facial responses.

“So far no electrodes have been sensitive enough to measure these contortions,” Prof. Levy claimed.

The 40 trial participants were asked to sit in pairs facing one another, with one wearing headphones through which the words “line” or “tree” were transmitted. When the participant wearing headphones heard “line” but reported “tree,” or vice versa, his partner’s task was to try and detect the fib. Then, the pair switched roles.

The results showed that participants were not able to uncover their partners’ lies with any statistical significance, but that electrical signals coming from the electrodes attached to their face could do so — with an accuracy of 73%. The research has been peer-reviewed and published in the Brain and Behavior journal.

“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,” said Levy. “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.”