Towards protecting biometric templates without sacrificing performance

Fuzzy Commitments Offer Insufficient Protection to Biometric Templates Produced by Deep Learning

IEEE Transactions on Information Forensics and Security ◽

10.1109/tifs.2021.3103056 ◽

2021 ◽

pp. 1-1

Author(s):

Danny Keller ◽

Margarita Osadchy ◽

Orr Dunkelman

Keyword(s):

Deep Learning ◽

Biometric Templates

Download Full-text

Secure Online Examination with Biometric Authentication and Blockchain-Based Framework

Mathematical Problems in Engineering ◽

10.1155/2021/5058780 ◽

2021 ◽

Vol 2021 ◽

pp. 1-12

Author(s):

Xiaoling Zhu ◽

Chenglong Cao

Keyword(s):

Access Control ◽

Biometric Authentication ◽

Fine Grained ◽

Fuzzy Vault ◽

Malicious Behavior ◽

Online Examination ◽

E Learning ◽

Important Means ◽

Biometric Templates ◽

Biometric Features

E-learning has been carried out all over the world and then online examinations have become an important means to check learning effect during the outbreak of COVID-19. Participant authenticity, data integrity, and access control are the assurance to online examination. The existing online examination schemes cannot provide the protection of biometric features and fine-grained access control. Particularly, they did not discuss how to resolve some disputes among students, teachers, and a platform in a fair and reasonable way. We propose a novel biometric authentication and blockchain-based online examination scheme. The examination data are encrypted to store in a distributed system, which can be obtained only if the user satisfies decryption policy. And the pieces of evidence are recorded in a blockchain network which is jointly established by some credible institutions. Unlike other examination authentication systems, face templates in our scheme are protected using a fuzzy vault and a cryptographic method. Furthermore, educational administrative department can determine who the real initiator of malicious behavior is when a dispute arises using a dispute determination protocol. Analysis shows that no central authority is required in our scheme; the collusion of multiple users cannot obtain more data; even if the authorities compromise, biometric features of each user will not be leaked. Therefore, in terms of privacy-preserving biometric templates, fine-grained access, and dispute resolution, it is superior to the existing schemes.

Download Full-text

Privacy-Aware Processing of Biometric Templates by Means of Secure Two-Party Computation

Security and Privacy in Biometrics ◽

10.1007/978-1-4471-5230-9_7 ◽

2013 ◽

pp. 149-185

Author(s):

Riccardo Lazzeretti ◽

Pierluigi Failla ◽

Mauro Barni

Keyword(s):

Biometric Templates

Download Full-text

VARIABILIDADE GENÉTICA UTILIZANDO DESCRITORES MORFOLÓGICOS PARA ACESSOS DE Capsicum spp. PARA FINS ORNAMENTAIS

Nativa ◽

10.31413/nativa.v7i6.7984 ◽

2019 ◽

Vol 7 (6) ◽

pp. 675

Author(s):

Petterson Baptista da Luz ◽

Alessandro Aparecido Brito dos Santos ◽

Valdete Campos Ambrosio

Keyword(s):

Genetic Variability ◽

Ornamental Plants ◽

Growth Potential ◽

Breeding Programs ◽

Canonical Correlations ◽

Plant Parts ◽

Potted Plants ◽

Capsicum Spp ◽

Biometric Templates

O mercado de pimentas para fins ornamentais é um setor recém explorado, mas com grande potencial de crescimento no ramo de floricultura e paisagismo. As pimenteiras que possuem folhagem variegada, porte baixo, frutos com coloração variada em seus diferentes estádios de maturação, contrastando com as folhagens, já são utilizadas como plantas ornamentais, cultivadas e comercializadas em vasos. O presente trabalho teve como objetivo avaliar a variabilidade genética visando o potencial ornamental de acessos de Capsicum spp. através de modelos biométricos. Foram utilizados 55 acessos de Capsicum spp, e a caracterização morfoagronômica dos acessos foi realizada avaliando diferentes partes da planta. O terceiro par de correlações canônicas, com correlação de 0,51, associa plantas com área do dossel compacto-densa, com menor comprimento e largura de dossel e de pequeno porte, associado com folhagens estreitas e de pecíolo grande. Esta associação é vantajosa para ornamentação. Ficou evidenciada a presença de variabilidade genética na população, o que é bastante favorável ao melhoramento na medida em que a heterogeneidade genética possibilita a obtenção de ganhos por meio de seleção.Palavras-chave: pimenta; modelos biométricos; correlações canônicas; análise de trilha. GENETIC VARIABILITY FOCUSED ON ORNAMENTAL POTENTIAL OF A Capsicum spp. ACCESSION ABSTRACT: Pepper market for ornamental purposes is recently exploited; however, it has a great growth potential in floriculture and landscaping. Pepper with variegated foliage, small size, and varied fruit coloration at different ripening stages contrasting with leaves have already been used as ornamental plants cultivated and purchased as potted plants. This study aimed to evaluate genetic variability of Capsicum spp. focusing on its ornamental potential by means of biometric templates. Fifty-five Capsicum spp. accessions were used and a morpho-agronomic characterization of the accessions were performed by evaluating different plant parts. The third canonical correlations are 0.51 and it associates compact-dense, small, shorter length and width canopy plants with narrow foliage and large petiole, which is advantageous for ornamentation. Genetic variation was evidenced in the population being very favorable for plant breeding programs once genetic heterogeneity enables obtaining gains through selections.Keywords: pepper; biometric templates; canonic correlations; trail analysis.

Download Full-text

Discrete Transforms and Matrix Rotation Based Cancelable Face and Fingerprint Recognition for Biometric Security Applications

Entropy ◽

10.3390/e22121361 ◽

2020 ◽

Vol 22 (12) ◽

pp. 1361

Author(s):

Abeer D. Algarni ◽

Ghada El Banby ◽

Sahar Ismail ◽

Walid El-Shafai ◽

Fathi E. Abd El-Samie ◽

...

Keyword(s):

Fourier Transform ◽

Fractional Fourier Transform ◽

Fingerprint Recognition ◽

Discrete Wavelet ◽

Security Level ◽

Cancelable Biometrics ◽

Security Applications ◽

Discrete Transforms ◽

Transform Domains ◽

Biometric Templates

The security of information is necessary for the success of any system. So, there is a need to have a robust mechanism to ensure the verification of any person before allowing him to access the stored data. So, for purposes of increasing the security level and privacy of users against attacks, cancelable biometrics can be utilized. The principal objective of cancelable biometrics is to generate new distorted biometric templates to be stored in biometric databases instead of the original ones. This paper presents effective methods based on different discrete transforms, such as Discrete Fourier Transform (DFT), Fractional Fourier Transform (FrFT), Discrete Cosine Transform (DCT), and Discrete Wavelet Transform (DWT), in addition to matrix rotation to generate cancelable biometric templates, in order to meet revocability and prevent the restoration of the original templates from the generated cancelable ones. Rotated versions of the images are generated in either spatial or transform domains and added together to eliminate the ability to recover the original biometric templates. The cancelability performance is evaluated and tested through extensive simulation results for all proposed methods on a different face and fingerprint datasets. Low Equal Error Rate (EER) values with high AROC values reflect the efficiency of the proposed methods, especially those dependent on DCT and DFrFT. Moreover, a comparative study is performed to evaluate the proposed method with all transformations to select the best one from the security perspective. Furthermore, a comparative analysis is carried out to test the performance of the proposed schemes with the existing schemes. The obtained outcomes reveal the efficiency of the proposed cancelable biometric schemes by introducing an average AROC of 0.998, EER of 0.0023, FAR of 0.008, and FRR of 0.003.

Download Full-text