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's thread
view the rest of the comments
[–] 23 points 3 years ago (1 child)

You have to train it on per device + per room basis and you don't give everything access to your microphones

  • source
  • hideshow 2 child comments
  • [–] 12 points 3 years ago* (1 child)

    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.

  • source
  • parent
  • hideshow 2 child comments