A lightweight approach for biometric template protection

Al-Assam, Hisham; Sellahewa, Harin; Jassim, Sabah

doi:10.1117/12.818291

Cited by 24 publications

(19 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed protection is one of the unitary transform-based template protection. Therefore, the protected templates have the following properties under p i = p j [6].…”

Section: B Dft-based Template Protectionmentioning

confidence: 99%

“…A lot of generation schemes of Q p i have been studied to generate unitary or orthogonal random matrices [5], [6], [8]. For example, the Gram-Schmidt method is applied to a pseudo-random matrix to generate Q p i [8].…”

Section: A Unitary Transform-based Template Protectionmentioning

confidence: 99%

“…For example, the Gram-Schmidt method is applied to a pseudo-random matrix to generate Q p i [8]. However, generally, the conventional schemes are computationally expensive [5], [6].…”

Section: A Unitary Transform-based Template Protectionmentioning

confidence: 99%

See 2 more Smart Citations

Unitary Transform-Based Template Protection and Its Application to l2-norm Minimization Problems

Nakamura

Tonomura

Kiya

2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYWe focus on the feature transform approach as one methodology for biometric template protection, where the template consists of the features extracted from the biometric trait. This study considers some properties of the unitary (including orthogonal) transform-based template protection in particular. It is known that the Euclidean distance between the templates protected by a unitary transform is the same as that between original (non-protected) ones as a property. In this study, moreover, it is shown that it provides the same results in l 2 -norm minimization problems as those of original templates. This means that there is no degradation of recognition performance in authentication systems using l 2 -norm minimization. Therefore, the protected templates can be reissued multiple times without original templates. In addition, a DFT-based template protection scheme is proposed as an unitary transform-based one. The proposed scheme enables to efficiently generate protected templates by the FFT, in addition to the useful properties. It is also applied to face recognition experiments to evaluate the effectiveness.

show abstract

“…The proposed protection is one of the unitary transform-based template protection. Therefore, the protected templates have the following properties under p i = p j [6].…”

Section: B Dft-based Template Protectionmentioning

confidence: 99%

Section: A Unitary Transform-based Template Protectionmentioning

confidence: 99%

See 1 more Smart Citation

Unitary Transform-Based Template Protection and Its Application to l2-norm Minimization Problems

Nakamura

Tonomura

Kiya

2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…In this paper, we focus on the first category (i.e. feature transformation), and more precisely on Random Orthonormal Projection (ROP) proposed in [7,8]. ROP technique relies on user-based orthonormal matrices to transform individual's biometric features (points in high dimensional space) to a secure space where the distances between original points and the secure ones are preserved.…”

Section: Background and Related Workmentioning

confidence: 99%

“…Precisely, FingerCode approach proposed by Jain eta al in [16] has been selected due to the fact that Random Orthonormal Projection (ROP) [7,8] requires fixed length feature vectors. FingerCode approach [16] relies on detecting the Region Of Interest (ROI) and tessellating it around the reference point, then a bank of Gabor filters are applied in eight directions to capture both local and global features of a fingerprint image as illustrated by Figure 1.…”

Section: Biometric Authentication and Key Generationmentioning

confidence: 99%

Privacy preserving, real-time and location secured biometrics for mCommerce authentication

et al. 2011

Self Cite

View full text Add to dashboard Cite

Secure wireless connectivity between mobile devices and financial/commercial establishments is mature, and so is the security of remote authentication for mCommerce. However, the current techniques are open for hacking, false misrepresentation, replay and other attacks. This is because of the lack of real-time and current-precise-location in the authentication process. This paper proposes a new technique that includes freshly-generated real-time personal biometric data of the client and present-position of the mobile device used by the client to perform the mCommerce so to form a real-time biometric representation to authenticate any remote transaction. A fresh GPS fix generates the "time and location" to stamp the biometric data freshly captured to produce a single, real-time biometric representation on the mobile device. A trusted Certification Authority (CA) acts as an independent authenticator of such client's claimed realtime location and his/her provided fresh biometric data. Thus eliminates the necessity of user enrolment with many mCommerce services and application providers. This CA can also "independently from the client" and "at that instant of time" collect the client's mobile device "time and location" from the cellular network operator so to compare with the received information, together with the client's stored biometric information. Finally, to preserve the client's location privacy and to eliminate the possibility of cross-application client tracking, this paper proposes shielding the real location of the mobile device used prior to submission to the CA or authenticators.

show abstract