Keyboard acoustic side channel attacks: exploring realistic and security-sensitive scenarios

This research takes a closer look at keyboard acoustic emanations specifically for the purpose of eavesdropping over random passwords. In this scenario, dictionary and HMM language models are not applicable; the attacker can only utilize the raw acoustic information which has been recorded. This work investigates several existing signal processing techniques for this purpose and introduces a novel technique—time–frequency decoding—that improves the detection accuracy compared to previous techniques. It also carefully examines the effect of typing style—a crucial variable largely ignored by prior research—on the detection accuracy. The results show that using the same typing style (hunt and peck) for both training and decoding the data, the best case success rate for detecting correctly the typed key is 64 % per character. The results also show that changing the typing style, to touch typing, during the decoding stage reduces the success rate, but using the time–frequency technique, it is still possible to achieve a success rate of around 40 % per character. In these realistic scenarios, where the password is random, the approach described here can reduce the entropy of the search space by up to 57 % per character. This brings keyboard acoustic attack one step closer to a full-fledged vulnerability.