Continuous authentication for the user based on Keystroke Dynamics (Applied to commonly and rarely used Arabic words)

Abstract

Continuous Authentication considered as one of the authentication methods that has been emerged to solve the problem verifying whether who is using the system is the same one from the moment of login to the moment of logout, Keystroke Dynamics is one of the continuous authentication methods that can be used for authentication either in the form of fixed text or free text. The purpose of this paper is to study the possibility of using specific Arabic words to authenticate the user continuous authentication based on Keystroke Dynamics, as well as to examine the differences between the performance of the authentication system when using the commonly used words in authentication and its performance when using rarely used words in authentication.  In this study, one of the continuous authentication algorithms based on Keystroke Dynamics has been applied to ten Arabic words of commonly used words in e-mail, and three Arabic words which are rarely used, where four of the timing characteristics were used to extract the features of the typing style of users on the keyboard. To classify user's data, a measure of distance from the statistical approach, which is the Scaled Manhattan distance measure, Individual threshold, trust level and Tlockout were used. The results have shown that it is possible to authenticate users using continuous authentication based on the Arabic Language Keystroke Dynamics of fixed text .