Devices that outperform humans and expose their lies with 73% accuracy

Scientists have been trying to come up with an accurate way to detect that someone has been lying or cheating on a target for decades and now, thanks to artificial intelligence, scientists think they may be close to hitting the target by a significant percentage.

Devices that outperform humans and expose their lies with 73% accuracy
Artificial intelligence can detect deception

According to the British “Daily Mail”, quoting the leading Brain and Behavior magazine, a team of scientists managed to create sensors in able to read the faces of a number of volunteers, and to monitor and monitor slight changes in facial movement while telling lies or true facts.

73% accuracy

The artificial intelligence system was in able to tell if someone was lying with 73% accuracy, which is a little less than test of the polygraph, which reached a degree of accuracy of 80%, but scientists say that this percentage was reached very early stage of the experiment, which means that it will be improved in future.

Tel Aviv University scientists expect that in future, cameras equipped with artificial intelligence can be used in airports, in job interviews online or in police interrogations of suspects to see if anyone is lying.

Devices are superior to humans

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

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

Facial movements were measured using stickers printed on soft surfaces containing electrodes in able to monitor and measure nerves and muscles. Researchers attached the stickers to the cheek muscles near the lips and to the muscles above the eyebrows.

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

Dramatic effects

The researchers expect the innovative artificial intelligence program to have “dramatic effects in many areas of life “, as electrodes may be available in abundance in future and therefore could be used in conjunction with software video to detect lies by observing the movements of the facial muscles.

It will thus be possible to use the innovative technology in the “banking, interrogation in police departments, airports or in job interviews” sectors. online, [إذ] High-resolution cameras trained to identify facial muscle movements will be in degree of [تحديد ما إذا كانت] Truthful statements from lies. “

Criticisms in past

The idea of ​​using artificial intelligence to detect liars has been criticized in past. For example, in 2018, researchers at Manchester Metropolitan University suggested that artificial intelligence could be used to detect whether people are lying to border security by analyzing their precise gestures, but the professor Ray Paul, a professor of criminal investigation at the University of Derby, criticized the idea, saying it was a project. It lacks credibility, because there aren’t any prove that observing small changes in people’s faces is an accurate way to measure the lie.

The professor Ball said: “Them [علماء جامعة مانشستر متروبوليتان] They delude themselves into thinking that they will never be very 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 deceptive.

Read More About: Technology News