Researchers in the UK claim to have translated the sound of laptop keystrokes into their corresponding letters with 95 percent accuracy in some cases.
That 95 percent figure was achieved with nothing but a nearby iPhone. Remote methods are just as dangerous: over Zoom, the accuracy of recorded keystrokes only dropped to 93 percent, while Skype calls were still 91.7 percent accurate.
In other words, this is a side channel attack with considerable accuracy, minimal technical requirements, and a ubiquitous data exfiltration point: Microphones, which are everywhere from our laptops, to our wrists, to the very rooms we work in.
Idk how it works with non-NVIDIA GPUs but get Nvidia Broadcast or an equivalent. Its a life saver.
macOS Sonoma has just updated with camera effects/reactions and "voice isolation" which works just like NVIDIA Broadcast/RTX Voice, luckily.
It doesn't do a very good job of removing my keyboard noise for some reason, and it makes my voice sound noticably worse ๐
Mines perfect, my baby can't even scream in my mic. It gets caught. I don't recall messing with settings, and my GPU is a 2080 TI. Idk, hardware maybe? Theres not much to mess with.