Scientists at [tag]UC Berkeley[/tag] have finished a study on using a [tag]parabolic[/tag] microphone to record the audible version of your keystrokes and based on the sound of the “clicks”, decipher what it is that your typing with stunning accuracy.
“Using statistical learning theory, the computer can categorize the sounds of each key as it’s struck and develop a good first guess with an accuracy of 60 percent for characters, and 20 percent for words,” said [tag]Li Zhuang[/tag], a UC Berkeley Ph.D. student in computer science and lead author of the study. “We then use spelling and grammar checks to refine the results, which increased the character accuracy to 70 percent and the word accuracy to 50 percent. The text is somewhat readable at this point.”
The recording is then passed through several more filters in a loop until no more significant improvement is seen. This results in “recovery rates of 88 percent for words and 96 percent for characters” on average.
so, basically, anyone with a parabolic microphone and the time to read and decipher the scientific algorithims that they used and published in this report can now keylog from just about anywhere. Theoretically, a recording could be made from the next cubicle or from the next building.
Scary stuff, but it should result in a push for more and better biometric resources for security.
News article here.
[tags]Keystroke, Keystroke logging[/tags]