A group of scientists from the University of Glasgow have developed a system based on artificial intelligence that Guess a user’s password in seconds By detecting heat trace of fingers on keyboard and screen.
The system called ThermoSecure, especially with the increasing use of artificial intelligence, as the university in a press release, reveals the risks of thermal attacks in cybersecurity.
Password theft via thermal attack does not require expert knowledge, only look at thermal images From a computer strategically placed next to a screen or keyboard into which password characters are entered.
Picture Will show the keys pressed by the user in colors, being the brighter ones pulsed recently. A person’s password can be viewed with a careful eye 30 to 60 seconds after it is entered.
The developed system is capable Identify 16 character long passwords in 20 seconds At the rate of 67 percent of correct attempts. In shorter passwords, the success rate increases; This increases to 82 percent with 12-character keys and to 93 percent with eight characters.
If the password is reduced to six characters, the chance of success increases to 100 percent, according to the press release.
style of User typing also contributesSo that a person who types slowly and keeps their fingers on the surface of the keys longer will create a more durable heat signature.
it also affects the material of which the keyboard is made, as it affects the ability to retain heat. Thus, the study indicates that keyboards made of ABS plastic reduce the guessing success several times, whereas in the case of PBT plastic, the success is about 14 percent of the effort.
Sign up for our newsletter and receive the latest tech news in your email.