Unlinkable and irreversible biometric template protection based on bloom filters

New framework for the analysis of the unlinkability of protected templates.New unlinkable and irreversible biometric template protection scheme.Biometric Template Protection scheme robust to cross-matching attacks.Thorough eval of compliance with ISO/IEC IS 24745- biometric inf protection. Deployments of biometric technologies are already widely disseminated in numerous large-scale nation-wide projects. Since the protection of biometric reference data is of particular concern in order to safeguard individuals' privacy, biometric template protection schemes are designed to handle biometric reference data in an irreversible and unlinkable manner. In past years, schemes based on Bloom filters have been introduced and applied to various characteristics. However, thorough security analyses have exposed the original concept to be vulnerable to cross-matching attacks.In this article we present a general framework for the evaluation of unlinkability in biometric template protection schemes, as well as an improved, unlinkable and irreversible, system based on Bloom filters. In order to generate cross-matching resistant protected templates we re-design the original scheme and propose an additional, easily integrable, processing step, which is referred to as structure-preserving feature re-arrangement. The improved system is thoroughly evaluated on the publicly available face corpus of the BioSecure Multimodal Database. It is shown that the proposed scheme maintains the biometric performance of the unprotected system. Moreover, cross-matching resistance is achieved in the presence of existing attacks, considering adversary models where potential attackers are in possession of protected biometric templates as well as secret credentials.

[1]  Julien Bringer,et al.  Security analysis of Bloom filter-based iris biometric template protection , 2015, 2015 International Conference on Biometrics (ICB).

[2]  Andrew Beng Jin Teoh,et al.  Cancellable biometrics and annotations on BioHash , 2008, Pattern Recognit..

[3]  Shantanu Rane,et al.  Standardization of Biometric Template Protection , 2014, IEEE MultiMedia.

[4]  Christoph Busch,et al.  Towards generating protected fingerprint templates based on bloom filters , 2015, 3rd International Workshop on Biometrics and Forensics (IWBF 2015).

[5]  Wen Gao,et al.  Local Gabor binary pattern histogram sequence (LGBPHS): a novel non-statistical model for face representation and recognition , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[6]  R. A. Leibler,et al.  On Information and Sufficiency , 1951 .

[7]  Rama Chellappa,et al.  Cancelable Biometrics: A review , 2015, IEEE Signal Processing Magazine.

[8]  Alex Stoianov,et al.  Chapter 26. Biometric Encryption: The New Breed of Untraceable Biometrics , 2009 .

[9]  Sébastien Marcel,et al.  Bob: a free signal processing and machine learning toolbox for researchers , 2012, ACM Multimedia.

[10]  Nemanja Maček,et al.  An Efficient Approach to Generating Cryptographic Keys from Face and Iris Biometrics Fused at the Feature Level , 2015 .

[11]  Anil K. Jain.  Technology: Biometric recognition , 2007, Nature.

[12]  Christoph Busch,et al.  Alignment-free cancelable iris biometric templates based on adaptive bloom filters , 2013, 2013 International Conference on Biometrics (ICB).

[13]  Anil K. Jain,et al.  Biometric Template Protection: Bridging the performance gap between theory and practice , 2015, IEEE Signal Processing Magazine.

[14]  Javier Ortega-Garcia,et al.  Bayesian analysis of fingerprint, face and signature evidences with automatic biometric systems. , 2005, Forensic science international.

[15]  G. Radhamani,et al.  Multimodal Biometric Cryptosystem for Face and Ear Recognition Based on Fuzzy Vault , 2014 .

[16]  Nur Izura Udzir,et al.  Face Recognition and Template Protection with Shielding Function , 2015 .

[17]  Andrew Beng Jin Teoh,et al.  Personalised cryptographic key generation based on FaceHashing , 2004, Comput. Secur..

[18]  Christoph Busch,et al.  Towards cancelable multi-biometrics based on bloom filters: a case study on feature level fusion of face and iris , 2015, 3rd International Workshop on Biometrics and Forensics (IWBF 2015).

[19]  Bart Preneel,et al.  Criteria towards metrics for benchmarking template protection algorithms , 2012, 2012 5th IAPR International Conference on Biometrics (ICB).

[20]  Burton H. Bloom,et al.  Space/time trade-offs in hash coding with allowable errors , 1970, CACM.

[21]  Bart Mennink,et al.  When a Bloom filter is a Doom filter: Security assessment of a novel iris biometric template protection system , 2014, 2014 International Conference of the Biometrics Special Interest Group (BIOSIG).

[22]  Terrance E. Boult,et al.  Robust distance measures for face-recognition supporting revocable biometric tokens , 2006, 7th International Conference on Automatic Face and Gesture Recognition (FGR06).

[23]  Nalini K. Ratha,et al.  Enhancing security and privacy in biometrics-based authentication systems , 2001, IBM Syst. J..

[24]  Narishige Abe,et al.  Irreversible fingerprint template using Minutiae Relation Code with Bloom Filter , 2015, 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems (BTAS).

[25]  Andreas Uhl,et al.  A survey on biometric cryptosystems and cancelable biometrics , 2011, EURASIP J. Inf. Secur..

[26]  Kar-Ann Toh,et al.  A Method to Enhance Face Biometric Security , 2007, 2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems.

[27]  N. Lalithamani,et al.  Technique to Generate a Face and Palm Vein-Based Fuzzy Vault for a Multi-Biometric Cryptosystem , 2014 .

[28]  Sébastien Marcel,et al.  An Open Source Framework for Standardized Comparisons of Face Recognition Algorithms , 2012, ECCV Workshops.

[29]  Marina L. Gavrilova,et al.  Multimodal biometric approach for cancelable face template generation , 2012, Defense + Commercial Sensing.

[30]  Anne M. P. Canuto,et al.  An effective template protection method for face and voice cancellable identification , 2014, Int. J. Hybrid Intell. Syst..

[31]  Julian Fiérrez,et al.  Protected Facial Biometric Templates Based on Local Gabor Patterns and Adaptive Bloom Filters , 2014, 2014 22nd International Conference on Pattern Recognition.

[32]  Jiankun Hu,et al.  Design of alignment-free cancelable fingerprint templates via curtailed circular convolution , 2014, Pattern Recognit..

[33]  Arun Ross,et al.  Privacy of Facial Soft Biometrics: Suppressing Gender But Retaining Identity , 2014, ECCV Workshops.

[34]  Alejandro F. Frangi,et al.  This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. , 2022 .