Scientists have been trying to develop an accurate way to detect whether someone is lying or cheating on a target for decades, and now, thanks to artificial intelligence, scientists think they’re at the target. may be close to completion by a significant percentage.

Artificial intelligence can detect deception

Citing the leading journal Brain and Behavior, published by the British “Daily Mail”, a team of scientists succeeded in creating a sensor that was able to read the faces of several volunteers, and detected and monitored slight changes in facial movements. . While they were telling lies or the truth.

73% accuracy

The artificial intelligence system was able to tell whether someone was lying with an accuracy of 73%, which is slightly less than the polygraph test, which reached a degree of accuracy as high as 80%, but scientists say that this percentage was achieved very quickly. Experimental phase, which means that it will be improved in the future.

Scientists at Tel Aviv University hope that in the future, AI-equipped cameras could be used at airports, in online job interviews or in police interrogations of suspects to see if someone is lying.

tools are better than humans

Previous research has shown that humans can lie to the truth with an estimated rate of around 55%, while a polygraph is up to 80% accurate, but these percentages are not enough to accept lie detector test results as evidence. are not. court, so researchers around the world are working on new solutions.

The researchers used machine learning and artificial intelligence programs to analyze small changes in muscle movements while lying down, including small movements of the cheek muscles and eyebrows.
Measurement of twitching of the facial muscles.

Facial movements were measured using stickers printed on soft surfaces containing electrodes capable of monitoring and measuring nerves and muscles. The researchers attached the stickers to the cheek muscles near the lips and the muscles above the browbones.

The study is based on the assumption that facial muscles twist when a person lies, and so far no electrode is sensitive enough to measure these twists, so the researchers based the lying on the EMG signals from the electrodes. Trained a machine-learning program to identify By applying this method, an accuracy of up to 73% was achieved, and this may not be ideal, but it is much better than other techniques used for the same purpose.

dramatic impact

The researchers hope the innovative AI program will have “dramatic effects in many areas of life,” as electrodes may become available in abundance in the future, and then with video software to detect lie by observing facial muscle movements. Can be used.

It will thus be possible to use innovative technology in the areas of “inquiries in banks, police departments, at airports or in online job interviews”. [إذ] High-resolution cameras trained to detect facial muscle movements [تحديد ما إذا كانت] Tell the truth from a lie.”

criticism in the past

The idea of ​​using artificial intelligence to detect liars has been criticized in the past. For example, in 2018, researchers at Manchester Metropolitan University suggested that AI could be used to detect whether people are lying for border security by analyzing their precise gestures, but criminals at the University of Derby. Professor Ray Paul, a professor of inquiry, criticized the idea. , saying it was a project. It lacks credibility, as there is no evidence that seeing small changes in people’s faces is an accurate way to measure lies.

Professor Ball said: “They [علماء جامعة مانشستر متروبوليتان] They confuse themselves into thinking they will ever be highly effective. They waste a lot of money,” because that technology is based on a fundamental misunderstanding of what human behavior can be like when they are honest and deceitful.