Abstract
In this paper, we present a hashing function for the application of face template protection, which improves the correctness of existing algorithms while maintaining the security simultaneously. The novel architecture constructed based on four components: a self-defined concept called padding people, Random Fourier Features, Support Vector Machine, and Locality Sensitive Hashing. The proposed method is trained, with one-shot and multi-shot enrollment, to encode the user’s biometric data to a predefined output with high probability. The predefined hashing output is cryptographically hashed and stored as a secure face template. Predesigning outputs ensures the strict requirements of biometric cryptosystems, namely, randomness and unlinkability. We prove that our method reaches the REQ-WBP (Weak Biometric Privacy) security level, which implies irreversibility. The efficacy of our approach is evaluated on the widely used CMU-PIE, FEI, andFERET databases; our matching performances achieve 100% genuine acceptance rate at 0% false acceptance rate for all three databases and enrollment types. To our knowledge, our matching results outperform most of the state-of-the-art results.
-
IEEE Keywords
- Face,
- Cryptography,
- Training,
- Support vector machines,
- Bioinformatics,
- Databases
Introduction
Nowadays, the robustness of most security systems rely on the strength of the cryptographic key (i.e., randomness, length). However, because it is challenging for a human being to remember complicated string, the user tends to use a simple and meaningful password, or store it in somewhere, which can possibly be predicted or stolen by an adversary. Meanwhile, various biometric traits (i.e., face [50], iris [27], signature [29]) have been found to contain an individual unique pattern that can be used for user authentication or recognition. Authentication based on a concept of ”who we are” is much more convenient than ”what we remember” or ”what we have”. With the growing usage of the biometric templates, its protection becomes vital.
Since biometric data is permanently associated with the user and cannot be changed, the protection schemes must *Corresponding author: Deokjai Choi {dchoi@jnu.ac.kr} satisfy requirements of unlinkability and irreversibility [32]. Unlinkability: From the same biometric data, various versions of protected templates could be generated (i.e., renewability, cancelability, revocability). There is no correlation between transformed templates (i.e., independent, not cross-matching). In addition, transformed templates must not reveal any information about the original biometrics. Irreversibility: It should be computationally hard to trace back the raw biometric data from the stored reference data (i.e., helper data, protected template). Ballard et al. [4] defined this requirement as the REQ-WBP security level (Weak Biometric Privacy). Because of intra-user variation property, biometrics cannot be handled effectively using information security techniques. Besides, this characteristic also leads to a high false acceptance rate. Therefore, designing methods that satisfy both the requirements of security and performance is the main challenge in biometric template protection [18]. Several methods [30][1][45] take advantage of Convolutional Neural Network (CNN) models to enhance their matching performances. However, due to the nature of deep learning, their system security levels are partly unprovable.
Conclusion
We proposed a hashing function that produces the predefined output for biometric samples belonging to the user. We achieved 100% GARs at the strict operating point of zero FAR when measuring by tunable matching method, and achieved high GARs (95∼99%) when evaluating by a fixed matching approach. The provable security level and outperforming results on several popular face benchmarks demonstrate the superiority and potentiality of our method.
Acknowledgment
We thank Thang Hoang and Van Thong Huynh for helpful advice. This research was supported by NRF2017R1D1A1B03035343 and funded by Vietnam National University HoChiMinh City (VNU-HCM) under grant number NCM2019-18-01.
About KSRA
The Kavian Scientific Research Association (KSRA) is a non-profit research organization to provide research / educational services in December 2013. The members of the community had formed a virtual group on the Viber social network. The core of the Kavian Scientific Association was formed with these members as founders. These individuals, led by Professor Siavosh Kaviani, decided to launch a scientific / research association with an emphasis on education.
KSRA research association, as a non-profit research firm, is committed to providing research services in the field of knowledge. The main beneficiaries of this association are public or private knowledge-based companies, students, researchers, researchers, professors, universities, and industrial and semi-industrial centers around the world.
Our main services Based on Education for all Spectrum people in the world. We want to make an integration between researches and educations. We believe education is the main right of Human beings. So our services should be concentrated on inclusive education.
The KSRA team partners with local under-served communities around the world to improve the access to and quality of knowledge based on education, amplify and augment learning programs where they exist, and create new opportunities for e-learning where traditional education systems are lacking or non-existent.
FULL Paper PDF file:
FEHash: Full Entropy Hash for Face Template ProtectionBibliography
author
Year
2020
Title
FEHash: Full Entropy Hash for Face Template Protection,
Publish in
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA, 2020, pp. 3527-3536,
Doi
10.1109/CVPRW50498.2020.00413.
PDF reference and original file: Click here
Somayeh Nosrati was born in 1982 in Tehran. She holds a Master's degree in artificial intelligence from Khatam University of Tehran.
Professor Siavosh Kaviani was born in 1961 in Tehran. He had a professorship. He holds a Ph.D. in Software Engineering from the QL University of Software Development Methodology and an honorary Ph.D. from the University of Chelsea.
Nasim Gazerani was born in 1983 in Arak. She holds a Master's degree in Software Engineering from UM University of Malaysia.
