Analysing Keystroke Dynamics Using Wavelet Transforms

This conference paper explores the use of wavelet transforms for analyzing keystroke dynamics as a means of enhancing smartphone security. With a significant number of smartphones lost each year, many of which are accessed by unauthorized users, there is a critical need for continuous monitoring to detect impersonation. Keystroke dynamics provide a promising approach to distinguishing between a phone’s owner and an imposter.

The paper introduces a novel feature extraction method using wavelet transforms to convert keystroke data into robust features for training classifiers. A comparative study demonstrates that classifiers trained on features extracted by wavelet transforms outperform those using traditional feature extraction methods. This method also presents a cost-effective and more reliable alternative to existing two-tier authentication systems, such as one-time passwords (OTPs), by enhancing the accuracy of user identification on smartphones.

Recommended citation: Islam, A., & Belhaouari, S. B. (2022). "Analysing Keystroke Dynamics Using Wavelet Transforms." In 2022 IEEE International Carnahan Conference on Security Technology (ICCST) (pp. 1--5). IEEE. https://doi.org/10.1109/ICCST52959.2022.9896483
Download Paper