Artificial Intelligence Recognizes Passwords by Click Sounds

British technology researchers have discovered a new hacking method based on artificial intelligence. This method accurately guesses passwords with an accuracy exceeding 90% by listening to what is typed on the keyboard.

This hacking method relies on AI’s ability to learn and recognize different keyboard sounds by using a built-in microphone on a smartphone that listens to keystrokes on a “MacBook Pro” device, allowing researchers to accurately identify passwords with very high precision.

Moreover, the researchers tested the accuracy of the artificial intelligence system during a Zoom call. They recorded keyboard keystrokes using the laptop computer’s microphone during the meeting and found that the artificial intelligence model accurately replicated keystrokes by 93%.

The researchers explained that over the past decade the number of microphones within range of keyboards has increased dramticly, making this task easier.

This AI model works by recognizing the unique patterns users press on their keyboard keys, including sound, intensity, and timing of each keystroke.

To test the concept,  the researchers used a MacBook Pro device, which helped the system recognize patterns by first pressing 36 individual keys 25 times each. They also used an iPhone 13 mini, placed 17 cm away from the keyboard, to record the sound of keystrokes in the initial test.

Scientists consider this new technology, which uses a combination of artificial intelligence, microphones, and video calls, to be a “greater threat to keyboards than ever before.”

Al Jundi

Please use portrait mode to get the best view.