Direct and indirect human computer interaction based biometrics

Roman V. Yampolskiy, University of Louisville
Venu Govindaraju, University at Buffalo, The State University of New York

Abstract

In this paper we survey the state of the art in direct and indirect human computer interaction based biometrics. Direct HCI biometrics are based on abilities, style, preference, knowledge, or strategy used by people while working with a computer. The indirect HCI-based biometrics are events that can be obtained by monitoring users' HCI behavior indirectly via observable low-level actions of computer software. We examine current research and analyze the types of features used to describe HCI behavior. After comparing accuracy rates for verification of users using different HCI-based biometric approaches we address privacy issues which arise with the use of HCI dependant biometrics. Finally, we present results of our experiments with direct and indirect HCI-based behavioral biometrics employed as a part of an intrusion detection system. © 2006 ACADEMY PUBLISHER.