Template Protection and Renewability for Dynamic Time Warping Based Biometric Signature Verification

In this article, the authors propose a protected on-line signature based biometric authentication system, where the original signature templates are protected by transforming them in a non-invertible way. Recovering the original biometrics from the stored data is thus computationally as hard as random guessing them. The transformed templates are compared employing a Dynamic Time Warping (DTW) matching strategy. The reported experimental results, evaluated on the public MCYT signature database, show that the achievable recognition rates are only slightly affected by the proposed protection scheme, which is able to guarantee the desired security and renewability for the considered biometrics. DOI: 10.4018/jdcf.2009062404 IGI PUBLISHING This paper appears in the publication, International Journal of Digital Crime and Forensics, Volume 1, Issue 4 edited by Chang-Tsun Li © 2009, IGI Global 701 E. Chocolate Avenue, Hershey PA 17033-1240, USA Tel: 717/533-8845; Fax 717/533-8661; URL-http://www.igi-global.com ITJ 5311 International Journal of Digital Crime and Forensics, 1(4), 40-57, October-December 2009 41 Copyright © 2009, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited. mentioned security and privacy concerns need to be carefully considered when implementing a biometric recognition system, by providing appropriate countermeasures to the possible attacks which can be perpetrated at the vulnerable points of the system (Ratha, Connell, & Bolle, 2001). The adopted measures should be able to enhance biometric data resilience against attacks, while allowing the matching to be performed efficiently, thus guaranteeing acceptable recognition performance. In this contribution, a protected on-line signature based verification system is proposed. Specifically, non-invertible transformations are applied to signature templates represented by time sequences, in order to guarantee the necessary security and to allow the generation of multiple templates from the same original one. The present article stems from the works by the authors in (Maiorana, Martinez-Diaz, Campisi, Ortega-Garcia, & Neri, 2008) and (Maiorana, Campisi, Ortega-Garcia, & Neri, 2008), and it exploits the capabilities of a Dynamic Time Warping (DTW) based matching strategy for the comparison of protected signature templates. Specifically, the article is organized as follows: in Section II the solutions which have been investigated in the recent past to secure biometric templates are analyzed. The non-invertible transformations employed to provide protection to the considered signature templates are described in Section III, while the details regarding the proposed protected on-line signature recognition system are given in Section IV. The experimental framework and the obtained results are shown in Section V, and some conclusions are drawn in Section VI. BioMetriC teMPlate seCuritY The unauthorized copy of the stored biometric data is probably the most dangerous threat regarding users’ privacy and security. Therefore, many solutions have been investigated in the recent past to secure biometric templates. Among them, the most promising approaches consist in the implementation of cancelable biometrics (Ratha, Connell, & Bolle, 2001). This expression is commonly referred to the application of intentional non-invertible and repeatable modifications to the original biometric templates. Specifically, a properly defined cancelable biometrics should satisfy the following requirements: Security: • it should be impossible or computationally unfeasible to obtain the original biometric template from the transformed one; • Revocability: it should be possible to revoke a compromised template and issue a new one based on the same biometric data; • Diversity: each template generated from a biometrics should not match with others previously generated from the same data; • Performance: the recognition performance of the protected system, in terms of False Rejection Rate (FRR) or False Acceptance Rate (FAR), should not degrade significantly with respect to an unprotected system. A classification of the already proposed approaches for the generation of secure and renewable biometrics has been presented in (Jain, Nandakumar, & Nagar, 2008). Specifically, two macro-categories, referred to as biometric cryptosystem and feature transformation approaches, have been introduced. Biometric cryptosystems (Uludag, Pankanti, & Jain, 2004) typically employ binary keys to secure the biometric templates, and during the process some public information, usually referred to as helper data, is created. This category can be further divided into key binding systems, where the helper data are obtained by binding a random binary key with the biometric template (Juels & Wattenberg, 1999), (Juels & Sudan, 2006), and key generation systems, where both the helper data and the cryptographic key are directly generated from the biometric template (Sutcu, Li, & Memon, 2007). Typically, these 16 more pages are available in the full version of this document, which may be purchased using the "Add to Cart" button on the product's webpage: www.igi-global.com/article/template-protection-renewabilitydynamic-time/37424?camid=4v1 This title is available in InfoSci-Journals, InfoSci-Journal Disciplines Computer Science, Security, and Information Technology. Recommend this product to your librarian: www.igi-global.com/e-resources/libraryrecommendation/?id=2