Title: Strategy-based behavioural biometrics: a novel approach to automated identification

Authors: Roman V. Yampolskiy, Venu Govindaraju

Addresses: Department of Computer Engineering and Computer Science, University of Louisville, JB Speed Hall, #106, Louisville, KY 40292, USA. ' Department of Computer Science and Engineering, CUBS, University at Buffalo, 520 Lee Entrance, Suite 202, Buffalo, NY 14228, USA

Abstract: Behavioural intrusion detection is a frequently used for insuring network security. We expand behaviour based intrusion detection approach to a new domain of game networks. Specifically, our research shows that a behavioural biometric signature can be generated based on the strategy used by an individual to play a game. We wrote software capable of automatically extracting behavioural profiles for each player in a game of Poker. Once a behavioural signature is generated for a player, it is continuously compared against player|s current actions. Any significant deviations in behaviour are reported to the game server administrator as potential security breaches.

Keywords: behavioural biometrics; dissimilarity functions; game strategy; biometric signature; automated identification; intrusion detection; game networks; behavioural profiles; poker; security.

DOI: 10.1504/IJCAT.2009.024593

International Journal of Computer Applications in Technology, 2009 Vol.35 No.1, pp.29 - 41

Published online: 10 Apr 2009 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article