Keystroke recognition using neural network

Abstract

This paper present a keystroke dynamics Biometrie system using neural network as its classifier to recognize an individual. Biometric scheme are being widely used as their security merits over the earlier authentication system based on their history, that is the records were easily lost, guessed or forget. Biometric is more complex than password and is unique for each individual. Keystroke dynamics, which distinguishes individual by its typing rhythm, is the most prevalent behavior biometric authentication system. In this work, the focus is made on the dwell time and flight time of the users' typing to recognize or reject an imposter. A multilayer perceptron (MLP) neural network is used to train and authenticate the features. The neural network classifier is used to evaluate the feature of the user. Based on the recognition rate of 98.5% achieved, the fusion of keystroke dynamic features along with Neural Network has proved to be a promising technique.