New acoustic attack steals data from keystrokes with 95% accuracy
![](https://lemmy.world/pictrs/image/7c668ec0-a3ad-455f-b736-1f5f13808b09.png)
![](https://fry.gs/pictrs/image/c6832070-8625-4688-b9e5-5d519541e092.png)
![](https://lemmy.world/pictrs/image/cc353f90-ec5f-4c39-853b-962c2cc7d20a.jpeg?format=jpg&thumbnail=256)
bleepingcomputer.com
New acoustic attack steals data from keystrokes with 95% accuracy::A team of researchers from British universities has trained a deep learning model that can steal data from keyboard keystrokes recorded using a microphone with an accuracy of 95%.
You are viewing a single comment
You have to train it on per device + per room basis and you don't give everything access to your microphones
I was just thinking, streamers might have to be careful actually — you can often both see and hear when they're typing, so if you correlated the two you could train a key audio → key press mapping model. And then if they type a password for something, even if it's off-screen from their stream, the audio might clue you in on what they're typing.
That could hypothetically be avoided by distorting the streamed audio just a tiny bit
Yeah. Or just use a password wallet.
Could be a fun honey pot.