Modified shielding function for multi-biometric authentication and template protection / Abayomi Jegede... [et al.]

Jegede, Abayomi and Udzir, Nur Izura and Abdullah, Azizol and Mahmod, Ramlan (2017) Modified shielding function for multi-biometric authentication and template protection / Abayomi Jegede... [et al.]. ESTEEM Academic Journal, 13. pp. 118-128. ISSN 1675-7939

Official URL: http://uppp.uitm.edu.my

Abstract

Biometrics provides a secure means of authentication because it is difficult to copy, forge, or steal biometric modalities. However, unprotected biometric data can be used to violate the security of the authentication system and the privacy of legitimate users. This paper proposes and implements a modified shielding function which provides multi-biometric authentication, template security and user privacy simultaneously. Experimental results based on face and iris datasets obtained from CASIA Near Infra-Red face database and CASIA Iris database version 2 respectively show that the approach has good recognition accuracy (false rejection rate of 0.65% and false acceptance rate of 0.035%). Security analysis shows that the method provides better security (key length of 120 bits) and user privacy compared to previous approaches based on the generic shielding function.

Metadata

Item Type: Article
Creators:
Creators
Email / ID Num.
Jegede, Abayomi
abayomi.jegede@ymail.com
Udzir, Nur Izura
UNSPECIFIED
Abdullah, Azizol
UNSPECIFIED
Mahmod, Ramlan
UNSPECIFIED
Subjects: T Technology > T Technology (General)
T Technology > T Technology (General) > Information technology. Information systems
Divisions: Universiti Teknologi MARA, Pulau Pinang > Permatang Pauh Campus
Journal or Publication Title: ESTEEM Academic Journal
ISSN: 1675-7939
Volume: 13
Page Range: pp. 118-128
Keywords: authentication; biometric; privacy; security; shielding function
Date: December 2017
URI: https://ir.uitm.edu.my/id/eprint/28840
Edit Item
Edit Item

Download

[thumbnail of AJ_ABAYOMI JEGEDE EAJ 17.pdf] Text
AJ_ABAYOMI JEGEDE EAJ 17.pdf

Download (313kB)

ID Number

28840

Indexing

|

Statistic

Statistic details