A Bioinformatics Based Approach to Behavioural Biometrics

Abstract

Behavioural biometrics is a scientific study with the primary purpose of identifying the authenticity of a user based on the way they interact with an authentication mechanism. There are several forms of behavioural biometrics such as voice analysis, signature verification, and keystroke dynamics. In this study, evidence is presented indicating that keystroke dynamics is a viable method not only for user verification, but also for identification as well. The work presented in this paper borrows ideas from the bioinformatics literature such as position specific scoring matrices (motifs) and multiple sequence alignments to provide a novel approach to user verification and identification within the context of a keystroke dynamics based user authentication system. The results in this study yield virtually 100% user authentication and identification within a single framework.