This paper presents a biometric system solution that "masks" a fraction of a person's biometric image before submission, to reduce the possibility of forgery and collusion. A prototype system was constructed for the fingerprint biometric and tested in three security scenarios. It is shown that implementing the fractional biometric system does not significantly affect accuracy. We provide theoretical security analysis on the guessing entropy of a Fractional Template and the security against collusion. We demonstrate that by masking above 50% of the biometric features, we achieve a sufficient mix of security, robustness and accuracy to warrant further study. When 75% of the features are masked, we found that the theoretical guessing entropy is 42 bits, and we found that, on average, 5 authenticators had to collude before the system would be compromised.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.