User Authentication by Keystroke Dynamics Using Machine Learning Algorithms

Abstract

Due to the expanding vulnerabilities in cyber forensics, security alone is not sufficient to forestall a rupture; however, cyber security is additionally required to anticipate future assaults or to distinguish the potential aggressor. Keystroke Dynamics has high use in cyber intelligence. The paper examines the helpfulness of keystroke dynamics to build up the individual personality. Three schemes are proposed for recognizing an individual while typing on keyboard. Lib SVM and binary SVM are proposed and their performance are shown. Lib SVM is showing a better performance when comparing with binary SVM. As the number of samples are increased it shows an increase in the accuracy. Pair wise user coupling technique is proposed. The proposed procedures are approved by utilizing keystroke information. In any case, these systems could similarly well be connected to other examples of pattern identification problems. This system is applicable in highly confidential areas like military.