Polynomial Based Fuzzy Vault Technique for
Template Security in Fingerprint Biometrics
Reza
Mehmood and Arvind Selwal
Department of Computer Science and Information Technology, Central
University of Jammu, India
Abstract: In recent years
the security breaches and fraud transactions are increasing day by day. So
there is a necessity for highly secure authentication technologies. The
security of an authentication system can be strengthened by using Biometric
system rather than the traditional method of authentication like Identity Cards
(ID) and password which can be stolen easily. A biometric system works on
biometric traits and fingerprint has the maximum share in market for providing
biometric authentication as it is reliable, consistent and easy to capture.
Although the biometric system is used to provide security to many applications
but it is susceptible to different types of assaults too. Among all the modules
of the biometric system which needs security, biometric template protection has
received great consideration in the past years from the research community due
to sensitivity of the biometric data stored in the form of template. A number
of methods have been devised for providing template protection. Fuzzy vault is
one of the cryptosystem based method of template security. The aim of fuzzy
vault technique is to protect the precarious data with the biometric template
in a way that only certified user can access the secret by providing valid
biometric. In this paper, a modified version of fuzzy vault is presented to
increase the level of security to the template and the secret key. The
polynomial whose coefficients represent the key is transformed using an
integral operator to hide the key where the key can no longer be derived if the
polynomial is known to the attacker. The proposed fuzzy vault scheme also
prevents the system from stolen key inversion attack. The results are achieved
in terms of False Accept Rate (FAR), False
Reject Rate (FRR), Genuine Acceptance Rate (GAR)
by varying the degree of polynomial and number of biometric samples. It was
calculated that for 40 users GAR was found to be 92%, 90%, 85% for degree of
polynomial to be 3, 4 and 5 respectively. It was observed that increasing the
degree of polynomial decreased the FAR rate, thus increasing the security.
Keywords: Biometrics,
Fingerprint, Template Security, Crypto-System, Fuzzy vault.