Key Classification: A New Approach in Free Text Keystroke Authentication System

Biometric methods are individual characteristics that cannot be used by imposters to enter in a secured system. Key stroke dynamics is a biometric utilizing the typing rhythm of the user. Key stroke dynamics is classified in two classes: (a) Fixed text based and (b) Free text based. We are proposing a novel technique for free text keystroke dynamics. In this method, keys are classified into two halves (left - right) and four lines (total eight groups) and then timing vectors (of flight time) are obtained between these key groups. Timing vectors are used to distinguish the legitimate user from imposters. The results obtained are very encouraging and supporting the approach followed in this work.