Investigating keystroke dynamics as a two-factor biometric security

Abstract

Keystroke dynamics is the study of how people can be distinguished based on their typing rhythms. This proposal aims at investigating user authentication approaches and how keystroke dynamics can be used to enhance user authentication and access control. With more users embracing technologies and using applications without necessarily understanding the security repercussions, a further protection mechanism needs to be employed. It emphasizes on the need of an additional layer of security, through keystroke dynamics, on top of the traditional username-password combination to enhance security during authentication. It also proposes the use of a machine learning classifier for possible application in keystroke dynamics to verify and validate the legitimacy of a user during authentication.