Typing pattern recognition using keystroke dynamics

Abstract

Biometric authentication is individual characteristics that cannot be used by imposter to penetrate secure system. Keystroke dynamics based authentication verifies user from their typing pattern. To authenticate user based on their typing samples, it is required to find out he resemblance of a typing samples of user regardless of the text typed. Key event timing is extracted from key features Latency, Dwell time, Key interval, Up to up, Flight time and standard are measure in the form of FAR, FRR and ER. In this paper we introduces a k-nearest neighbor approach to classify users' keystroke dynamics profiles. For authentication, an input will be checked against the profiles within the cluster which has significantly reduced the verification load. © 2013 Springer-Verlag.