Multi-datasets for different keyboard key sound recognition

Abstract

Keyboard acoustic recognition is a pivotal area within cybersecurity and human-computer interaction, where the identification and analysis of keyboard sounds are used to enhance security measures. The performance of acoustic-based security systems can be influenced by factors such as the platform used, typing style, and environmental noise. To address these variations and provide a comprehensive resource, we present the Multi-Keyboard Acoustic (MKA) Datasets. These extensive datasets, meticulously gathered by a team in the Computer Science Department at the University of Halabja, include recordings from six widely-used platforms: HP, Lenovo, MSI, Mac, Messenger, and Zoom. The MKA datasets have structured data for each platform, including raw recordings, segmented sound files, and matrices derived from these sounds. They can be used by researchers in keylogging detection, cybersecurity, and other fields related to acoustic emanation attacks on keyboards. Moreover, the datasets capture the intricacies of typing behaviour with both hands and all ten fingers by carefully segmenting and pre-processing the data using the Praat tool, thus ensuring high-quality and dependable data. This comprehensive approach allows researchers to explore various aspects of keyboard sound recognition, contributing to the development of robust recognition algorithms and enhanced security measures. The MKA Datasets stand as one of the largest and most detailed datasets in this domain, offering significant potential for advancing research and improving defences against acoustic-based threats.