Possibility of spoof attack against robustness of multibiometric authentication systems

Mahdi Hariri; Shahriar B. Shokouhi

doi:10.1117/1.3599874

1 July 2011 Possibility of spoof attack against robustness of multibiometric authentication systems

Mahdi Hariri, Shahriar B. Shokouhi

Author Affiliations +

Optical Engineering, Vol. 50, Issue 7, 079001 (July 2011). https://doi.org/10.1117/1.3599874

Abstract

Multibiometric systems have been recently developed in order to overcome some weaknesses of single biometric authentication systems, but security of these systems against spoofing has not received enough attention. In this paper, we propose a novel practical method for simulation of possibilities of spoof attacks against a biometric authentication system. Using this method, we model matching scores from standard to completely spoofed genuine samples. Sum, product, and Bayes fusion rules are applied for score level combination. The security of multimodal authentication systems are examined and compared with the single systems against various spoof possibilities. However, vulnerability of fused systems is considerably increased against spoofing, but their robustness is generally higher than single matcher systems. In this paper we show that robustness of a combined system is not always higher than a single system against spoof attack. We propose empirical methods for upgrading the security of multibiometric systems, which contain how to organize and select biometric traits and matchers against various possibilities of spoof attack. These methods provide considerable robustness and present an appropriate reason for using combined systems against spoof attacks.

©(2011) Society of Photo-Optical Instrumentation Engineers (SPIE)

Citation Download Citation

Mahdi Hariri and Shahriar B. Shokouhi "Possibility of spoof attack against robustness of multibiometric authentication systems," Optical Engineering 50(7), 079001 (1 July 2011). https://doi.org/10.1117/1.3599874

Published: 1 July 2011

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available