Paper says domain-invariant models recover keystrokes from keyboard audio
The authors say inference still works on unseen keyboards, users, noise, and compressed channels when a language model corrects predictions.
2 stories, newest first · one card per story
The authors say inference still works on unseen keyboards, users, noise, and compressed channels when a language model corrects predictions.
Unprivileged access to MacBook motion sensors can infer keystrokes with up to 97.5 percent accuracy.
Today 1.5K readers · 2.4K views · 754 reads · all time 189K views