Live data from Hacker News

AI can tell what you're typing by listening to the sound of your keyboard

theregister.com

11–20 of 23 posts

Re: AI can tell what you're typing by listening to the sound of your keyboard

#12
post #10

Earlier quoted context omitted.

Yeah, kind of makes you wonder how the audio isn't same quality in both since same hardware is used.

Potential variance of codecs, bitrates, and sampling rates, for starters.

93 vs 91.7 looks like a difference caused by statiscical error, let's say 93.0±1.0 vs 91.7±1.0. Are the error intevals published somewhere?

Re: AI can tell what you're typing by listening to the sound of your keyboard

#13
Obviously this has bigger implications than passwords, but the password discussion in the article made me realize I’ve never typed most of my passwords. I didn’t consider that as a benefit of password managers, but I’ll take it.

Re: AI can tell what you're typing by listening to the sound of your keyboard

#16

Good luck with me, I use 34 keys in a Colemak layout with 8 levels of layers, essentially rendering it all useless, many strokes are rolled into the next, and chorded combos will sound like one ambiguous click.

You were safe until you shared that with us, now they can just include your keyboard setup as an input embedding if they target you.

Re: AI can tell what you're typing by listening to the sound of your keyboard

#17

Can this tech be used for making powerless keyboards? As in no power just a mic.

This is a cool idea. Maybe you could make a keyboard specifically designed for this which made distinctive tones for each key like a xylophone. That would be a fun project.

Re: AI can tell what you're typing by listening to the sound of your keyboard

#19
post #2

> over Zoom, the accuracy of recorded keystrokes only dropped to 93 percent, while Skype calls were still 91.7 percent accurate. That's interesting considering the fact that Skype messenger is a well-known of its good (if not best) audio codec.

voice codecs get good performance by ignoring whatever noise isn't needed to reconstruct the voice.
Post reply on HN