Researchers at Tel Aviv University have developed a new advanced lie-detection system that exposes ‘liars’ through telltale activation of facial muscles. By using machine learning and AI, the new technology analyses small changes in facial muscle movements whenever a person says lies.
The technology relies on the novel stickers printed on soft surfaces containing electrodes that monitor and measure the activity of muscles and nerves associated with deception.
“Many studies have shown that it’s almost impossible for us to tell when someone is lying to us,” explains Prof. Dino Levy from the Coller School of Management. “Even experts, such as police interrogators, do only a little better than the rest of us. 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.”
In an experiment, researchers attached these stickers with their special electrodes to two groups of facial muscles: the cheek muscles close to the lips and the muscles over the eyebrows. The participants were paired up and asked to sit on the opposite side of one another, with one of them wearing headphones through which the words ‘line’ or ‘tree’ were transmitted.
The wearer was then asked to lie or tell the truth about what word they heard in the headphones, and his partner’s task was to try and detect the lie. As expected, participants were unable to detect their partners’ lies with any statistical significance. However, the electrical signals delivered by the electrodes attached to their face identified the lies at an unprecedented success rate of 73%.
“Since this was an initial study, the lie itself was very simple. Usually, when we lie in real life, we tell a longer tale which includes both deceptive and truthful components,” Prof. Levy said. “In our study, we had the advantage of knowing what the participants heard through the headsets, and therefore also knowing when they were lying. Thus, using advanced machine learning techniques, we trained our program to identify lies based on EMG (electromyography) signals coming from the electrodes. Applying this method, we achieved an accuracy of 73% – not perfect, but much better than any existing technology. Another interesting discovery was that people lie through different facial muscles: some lie with their cheek muscles and others with their eyebrows.”
The researchers believe that their lie-detection technology has great potential for detecting deception in real-life contexts, such as security and crime. In the future, the electrodes may become redundant, with video software trained to identify lies based on the actual movements of facial muscles.
Prof. Levy predicts, “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. 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.”