đź”´ August 7's Top Cyber News NOW! - Ep 424
Daily Cyber Threat Brief
00:00
The 95% Accuracy of Acoustic Attacks
Researchers trained a deep learning model that can steal data from keyboard keystrokes recorded using a microphone with an accuracy of 95%. When zoom was used for training the sound classification algorithm, the prediction accuracy dropped to 93%, which is still considered dangerously high. The researchers gathered training data by pressing 36 keys on a modern MacBook Pro 25 times each and recording the sound produced by each press.
Play episode from 23:07
Transcript
