Keyboard Sound Analysis Technology Provides Real Security Threat In The Future

Keyboard Sound Analysis Technology Provides Real Security Threat In The Future

It’s amazing just how much information can be translated from forensic sound recording analysis. Following a recent article by the economist about Doug Tygar and his colleagues at the University of California Berkeley, it appears that the sound of typing and clattering on your keyboard could be sending a message to untrustworthy parties.

The consistent tacking sound from a keyboard may seem the white noise of the modern age, but they betray more information than unwary typists may realise. Through using expert audio enhancement and analysis technology, computer scientists have managed to transcript blocks of text through analysing audio recordings of keyboard clatter. Alarmingly the information transcripted can often reveal secret security passwords and confidential information and in contrast to many types of computer espionage, the process is simple, requiring only a cheap microphone and a desktop computer.

Research from the University of California found that such forensic sound analysis could be possible due to the characteristic click produced by each key on a keyboard. Each key sound slightly differentiates itself from another due to its shape, position on keyboard, hand position of the wrists and the vigor the button is pressed. For example research has show the space bar, full stop and return button provide a higher toned noise when pressed that a letter key.

But past attempts to decipher keyboard sounds were only modestly successful, requiring a training session in which the computer matched a known transcript to an audio recording of each key being struck. Thus schooled, the software could still identify only 80% of the characters in a different transcript of the same typist on the same machine. Furthermore, each new typist or keyboard required a fresh transcript and training session, limiting the method’s appeal to would-be hackers.

A significant blow to acoustic security, Doug Tygar research published this month details an approach that reaches 96% accuracy, even without a labeled training transcript. The new approach employs methods developed for speech-recognition software to group together all the similar-sounding keystrokes in a recording, generating an alphabet of clicks.

The specialist software analysis technology assigns each click a letter based on its frequency, then tests the message created by this assignment using statistical models of the English language. For example, certain letters or words are more likely to occur together—if an unknown keystroke follows a “t”, it is much more likely to be an “h” than an “x”. Similarly, the words “for example” make likelier bedfellows than “fur example”. In a final refinement, the researchers employed a method many students would do well to deploy on term papers: automated spellchecking.

Despite the obvious security risks this technology carries including password theft and the ability to eavesdrop on other peoples conversations, with more laptops now equipped with microphones and cameras, simply typing away on your pc while linked to the web could be sending unwanted messages to hackers worldwide. Maybe it’s time we developed silent keyboards?

For more information on Audio Enhancement, Audio Analysis and Audio Investigation please visit Forensic Resources Ltd at http://www.forensicresources.co.uk/