Int. J. Biometrics, Vol. 10, No. 1, 2018 65
Copyright © 2018 Inderscience Enterprises Ltd.
An authentication system using keystroke dynamics
Farhana Javed Zareen, Chirag Matta,
Akshay Arora, Sarmod Singh and
Suraiya Jabin*
Department of Computer Science,
Jamia Millia Islamia, Central University,
New Delhi-110025, India
Email: farhanazareen@yahoo.com
Email: chirag1matta@gmail.com
Email: akshayaroraofficial@gmail.com
Email: baliyansarmod@gmail.com
Email: sjabin@jmi.ac.in
*Corresponding author
Abstract: There are various biometrics-based methods for user
authentication. However, the best authentication method can be based on
physiological/behavioural biometrics as capturing physiological biometrics
may require use of special devices and that may not be available with
many users. Keystroke dynamics is a simplified and easily achievable user
authentication method when every user is available with a laptop or a personal
computer. This paper presents a keystroke dynamics-based authentication
system using Bayesian regularised feed-forward neural network. In order to
train the model, a database is captured for recording keystroke dynamics of
20 users in four sessions each with 50 samples. Experimental results
demonstrate that the Bayesian regularised neural network models provide the
best results and are most suitable for this purpose. We are able to achieve an
equal error rate of 0.9% which is better than the methods used in the existing
literature for plain keystroke dynamics. We have given a comparative analysis
of the performance of proposed system with existing methods.
Keywords: individual authentication; biometrics; equal error rate; keystroke
dynamics; pattern recognition; machine learning.
Reference to this paper should be made as follows: Zareen, F.J., Matta, C.,
Arora, A., Singh, S. and Jabin, S. (2018) ‘An authentication system using
keystroke dynamics’, Int. J. Biometrics, Vol. 10, No. 1, pp.65–76.
Biographical notes: Farhana Javed Zareen is currently a PhD Scholar in
Department of Computer Science, Jamia Millia Islamia, Central University,
New Delhi, India. She received her Bachelor’s degree in 2010 and Master’s
degree in 2012 both from Department of Computer Science, Calcutta
University, India. Her research interests include artificial intelligence, pattern
recognition, and biometric signature verification.
Chirag Matta completed his Master’s in Computer Application (MCA) in 2016
from the Department of Computer Science, Jamia Millia Islamia, Central
University, New Delhi, India. He is currently serving as a Software Engineer in
Infogain India Pvt. Ltd.