Publication

Abstract : Mobile phones have become an integral part of everyone’s personal and professional life. Besides providing all the basic functions of a phone, most of the smart phone devices are also used to store critical information regarding a user like passwords, photos, bank account information, etc. Storing and accessing critical information and identifying legitimate users is becoming a growing challenge these days. Hence, authentication should be enforced for all mobile devices to identify legitimate users. We have based our study on behavioral biometrics specifically, touch dynamics. It and can be used to provide increased level of security when authentication is concerned and protection of mobile devices. The objective is to develop an authentication framework which uses a hybrid classification algorithm to classify legitimate users and imposters and to analyze the efficiency of the framework with existing ones. The process is performed on a publicly available touch dynamics dataset and important feature extraction is performed on the same. The accuracy of the scheme is measured on the basis of Equal Error Rate (EER).