Understanding users' keystroke patterns for computer access security

Abstract

User authentication is a major problem in gaining access rights for computer resources. A recent approach to enhance the computer access rights is the use of biometric properties as the keystroke rhythms of users. Therefore user authentication for computers can be more secure using keystroke rhythms as biometric authentication. Methods like minimum distance, statistical, vector based, neural network type and data mining techniques have been applied in analyzing the keystroke patterns. In this paper, a vector based algorithm for a recent approach has been applied in the identification of keystroke patterns. Keystroke Identification system that is a neuro physical characteristic is studied to realize biometric authentication.