zlacker

[return to "New acoustic attack steals data from keystrokes with 95% accuracy"]
1. mxwsn+WE[view] [source] 2023-08-05 21:00:15
>>mikece+(OP)
The example figure shows a key hit every half second, which suggests a pecking style of typing at around 24 wpm. This way the model gets very clean waveforms. I wonder how their approach would work with average or fast typists. The sound profiles might be much harder to link to characters.
◧◩
2. fbdab1+i41[view] [source] 2023-08-06 00:50:46
>>mxwsn+WE
Even if there was ambiguity, some data is better than none. Given enough training data, I suspect you could find repeatable patterns in standard typists: on a qwerty layout, after typing an "A", "Q" takes 1.2-2.3x as long to type as a "J" kind of pairwise tempo patterns. Anything to reduce the search space from brute-forcing every candidate character.

Even better if the target uses a passphrase, "hXXXse battXXX stXXXXX cXXXXXX" becomes interpretable given a few landmark letter identified with high probability.

[go to top]