kbd-audio VS system-bus-radio

You can try this at home with kbd-audio. No AI necessary.

https://github.com/ggerganov/kbd-audio

It's quite good at decoding my own typing, although I am a quite aggressive typist and that may help. I haven't tried it on others, though (honest, officer).

> Acoustic keyboard eavesdropping — ggerganov/kbd-audio

https://github.com/ggerganov/kbd-audio?ref=scopeofwork.net

Since when we talk, our tongues tap patterns on the roof of the mouth and the back of the teeth, I wonder if AI processing could infer what words you are shaping from these sensors. Maybe it’s possible to input text by mouthing words silently, but without opening your mouth. Kind of like how it’s possible to eavesdrop from just the sound of keyboard clicks:

https://github.com/ggerganov/kbd-audio

As opposed to AM: https://fulldecent.github.io/system-bus-radio/

https://github.com/fulldecent/system-bus-radio (out)

here is an example: https://fulldecent.github.io/system-bus-radio/

https://fulldecent.github.io/system-bus-radio/ - Tested on MacBook Air / Chrome with AM tuner at 1560 kHz. See field reports for other equipment and frequencies.

Probably because to get this stuff to work is really hard in practice.

Several years ago, we were playing with https://github.com/fulldecent/system-bus-radio to work, but we couldn't, even though we had the right MacBooks.

Have you gone fully paranoid and your air-gaped system is in a Faraday cage inside an anechoic chamber? Things like bus radio [1], coil whine and power fluctuations can be used (it has been shown) to exfiltrate data.

[1] https://github.com/fulldecent/system-bus-radio