Researchers have demonstrated a new acoustic side-channel attack on keyboards that can deduce user input based on their typing patterns, even in poor conditions, such as environments with noise.
Researchers have demonstrated a new acoustic side-channel attack on keyboards that can deduce user input based on their typing patterns, even in poor conditions, such as environments with noise. [...]
Looked at this a while ago. This has been a study for a while. Def interesting, but it requires time to train the model, and also it doesn't work on just any keyboard. Also isn't accurate always with figuring out what was typed and takes a lot of guesswork with machine learning.
you should probably read the article, it's different than other methods:
What makes the attack different compared to other approaches is that it can reach a typing prediction accuracy of 43% (on average) even when:
-the recordings contain environmental noise
-the recorded typing sessions for the same -target took place on different keyboard models
-the recordings were taken using a low-quality microphone
-the target is free to use any typing style
still only useful in extremely limited situations though... but it is neat that it uses timing of key strokes over the different sounds of each one...