A hybrid approach for face template protection

In identity management system, commonly used biometric recognition system needs attention towards issue of biometric template protection as far as more reliable solution is concerned.In view of this biometric template protection algorithm should satisfy security, discriminability and cancelability.As no single template protection method is capable of satisfying the basic requirements, a novel technique for face template generation and protection is proposed.The novel approach is proposed to provide security and accuracy in new user enrollment as well as authentication process.This novel technique takes advantage of both the hybrid approach and the binary discriminant analysis algorithm.This algorithm is designed on the basis of random projection, binary discriminant analysis and fuzzy commitment scheme.Three publicly available benchmark face databases are used for evaluation.The proposed novel technique enhances the discriminability and recognition accuracy by 80% in terms of matching score of the face images and provides high security.

Template-Protection-Techniken stellen eine wichtige Ergänzung zu biometrischen Systemen, um das gewünschte Sicherheitsniveau zu erreichen und die Anforderungen an den Schutz der Privatsphäre zu erfüllen. Diese Techniken ermöglichen Erneuerung und Widerruf der Referenzendaten in biometrischen Systemen. In dieser Arbeit wird ein systematisches Evaluierungsframework entwickelt, das sich an die wesentlichen Kriterien und Anforderungen an biometrische Template-Protection-Verfahren festhält. Seine Anwendbarkeit wird durch die Analyse der verschiedenen Algorithmen demonstriert. Die in dieser Arbeit präsentierte Evaluierung ist grundlegend für eine vollständige Analyse. Darüber hinaus ermöglicht es einen Nachweis der Sicherheit und Einhaltung der Privatsphäre. Es schafft eine Basis für Zertifizierung und Benchmark der Template-Protection-Verfahren.

The need for fool proof authentication procedures away from traditional authentication mechanisms like passwords, security PINS has led to the advent of biometric authentication in information systems. Biometric data extracted from physiological features of a person including but not limited to fingerprints, palm prints, face or retina for purpose of verification & identification is saved as biometric templates. The inception of biometrics in access control systems has not been without its own hitches & like other systems it has its fair share of challenges. Biometric fingerprints being the most mature of all biometric spheres are the most widely adopted biometric authentication systems. Biometric systems effectiveness lies on how secure they are at preventing inadvertent disclosure of biometric templates in an information system’s archive. This however has not been the case as biometric templates have been fraudulently accessed to gain unauthorized access in identification and verification systems. In order to achieve strong and secure biometric systems, biometric systems developers need to build biometric systems that properly secure biometric templates. Several biometric template protection schemes and approaches have been proposed and used to safeguard stored biometric templates. Despite there being various biometric template protection schemes and approaches in existence, none of them has provided the most authentic, reliable, efficient and deterrent means to totally secure biometric fingerprint templates. This research sought to establish status of the current biometric template protection techniques and methods by conducting a survey and analyzing data gathered from a sample of seventy-eight (78) respondents. We will report these results and give our conclusion based on findings of the survey in this paper.

The need to protect biometric data has been well advised according to various regulations and standards. The most popular Bloom Filter-based template protection schemes for iris recognition directly depend on the keys to avoid linkability challenges. This work presents a new approach for generating the keys directly from the iris biometric data using chaotic maps and elliptic curves over finite fields. Further, we present a new template protection scheme that can directly exploit the generated keys to provide better security using a Quarter-Rounded template encoding which employs the inter-relation of bits in the neighborhood of the iriscode. The proposed approach is validated on the publicly available IITD Iris database and the comparison to the state-of-art Bloom Filter template protection. The proposed approach achieves a comparable performance with the Bloom Filter template protection while eliminating key generation overhead. The proposed template creation approach achieves Genuine Match Rate (GMR) = 99.15% at FMR= 0.01% and EER= 0.77% on the IITD Iris database, with an unlinkability score of 0 and superior revocability.

Since the emergence of biometrics and its use in terms of authentication systems, the risks of fraud and identity theft keep increasing steadily. Hence, biometric template protection has become a real challenge for the research community. So several schemes have been proposed to address these issues and minimize the risk of attacks, but it turns out that just few of them have managed to satisfy both performance and security. In this context, we propose in our turn a fingerprint template protection, which consists of exploiting the minutiae structure that shapes the fingerprint, namely their positions and orientations, to then generate cancellable templates using a one-way transformation function. We proved that the proposal perfectly meets the properties of revocability, diversity, as well as accuracy performance. Promising results were obtained during an evaluation on FVC2002 DB1 database and which justifies the feasibility of our technique.

Data privacy is crucial when dealing with biometric data. Accounting for the latest European data privacy regulation and payment service directive, biometric template protection is essential for any commercial application. Ensuring unlinkability across biometric service operators, irreversibility of leaked encrypted templates, and renewability of e.g., voice models following the i-vector paradigm, biometric voice-based systems are prepared for the latest EU data privacy legislation. Employing Paillier cryptosystems, Euclidean and cosine comparators are known to ensure data privacy demands, without loss of discrimination nor calibration performance. Bridging gaps from template protection to speaker recognition, two architectures are proposed for the two-covariance comparator, serving as a generative model in this study. The first architecture preserves privacy of biometric data capture subjects. In the second architecture, model parameters of the comparator are encrypted as well, such that biometric service providers can supply the same comparison modules employing different key pairs to multiple biometric service operators. An experimental proof-of-concept and complexity analysis is carried out on the data from the 2013-2014 NIST i-vector machine learning challenge.

Theft of a template is theft of identity. Fingerprint identification is used by forensic department in identifying criminals because of its uniqueness. Biometrics is the science of verifying and establishing the identity of an individual through physiological features or behavioral traits. Fingerprint identification is commonly employed in Forensic science to support criminal investigations and in biometric systems such as civilian and commercial identification devices. The best way to identify criminals is using fingerprint verification which cannot be replaced. So such fingerprint acquired from the criminal should be safely stored and protected from hackers for future references. This paper mainly deals with protecting the criminal's record (fingerprint template). Templates represent intrinsic information about a criminal. The criminal record (Fingerprint template) should be protected from creation of physical spoof and replacement by imposter's template to gain unauthorized access. Due to these reasons, fool-proof techniques are required for securely storing the criminal fingerprint records. Fuzzy vault is a cryptographic construct that is designed to work with biometric features represented as an unordered set like minutiae points. Template protection is done by transformation based approaches and biometric cryptosystems. During transformation template is stored in a transformed form so that the original biometric template cannot be easily recovered. Fingerprint from the criminal is first preprocessed and minutiae points are extracted. Preprocessing is very essential because the creation of fuzzy vault highly depends on the quality of the input fingerprint image. Then image is binarized followed by thinning and then region of interest (ROI) is calculated finally followed by removal of false minutiae points. The remaining useful minutiae points are used in fuzzy vault generation. A polynomial is evaluated from the secret key which is combined with minutiae points to produce a secure vault. Some dummy points called chaff points are also added to increase the security. The security of the fuzzy vault depends on the infeasibility of the polynomial reconstruction and the number of chaff points. In the proposed system an even more secured fuzzy vault is generated with combined features of fingerprint and palm print to enhance the security of the template stored.

In a biometric authentication system using protected templates, a pseudonymous identifier is the part of a protected template that can be directly compared. Each compared pair of pseudonymous identifiers results in a decision testing whether both identifiers are derived from the same biometric characteristic. Compared to an unprotected system, most existing biometric template protection methods cause to a certain extent degradation in biometric performance. Fusion is therefore a promising way to enhance the biometric performance in template-protected biometric systems. Compared to feature level fusion and score level fusion, decision level fusion has not only the least fusion complexity, but also the maximum interoperability across different biometric features, template protection and recognition algorithms, templates formats, and comparison score rules. However, performance improvement via decision level fusion is not obvious. It is influenced by both the dependency and the performance gap among the conducted tests for fusion. We investigate in this paper several fusion scenarios (multi-sample, multi-instance, multi-sensor, multi-algorithm, and their combinations) on the binary decision level, and evaluate their biometric performance and fusion efficiency on a multi-sensor fingerprint database with 71,994 samples.

In recent years the security breaches and fraud transactions are increasing day by day. So there is a necessity for highly secure authentication technologies. The security of an authentication system can be strengthened by using Biometric system rather than the traditional method of authentication like Identity Cards (ID) and password which can be stolen easily. A biometric system works on biometric traits and fingerprint has the maximum share in market for providing biometric authentication as it is reliable, consistent and easy to capture. Although the biometric system is used to provide security to many applications but it is susceptible to different types of assaults too. Among all the modules of the biometric system which needs security, biometric template protection has received great consideration in the past years from the research community due to sensitivity of the biometric data stored in the form of template. A number of methods have been devised for providing template protection. Fuzzy vault is one of the cryptosystem based method of template security. The aim of fuzzy vault technique is to protect the precarious data with the biometric template in a way that only certified user can access the secret by providing valid biometric. In this paper, a modified version of fuzzy vault is presented to increase the level of security to the template and the secret key. The polynomial whose coefficients represent the key is transformed using an integral operator to hide the key where the key can no longer be derived if the polynomial is known to the attacker. The proposed fuzzy vault scheme also prevents the system from stolen key inversion attack. The results are achieved in terms of False Accept Rate (FAR), False Reject Rate (FRR), Genuine Acceptance Rate (GAR) by varying the degree of polynomial and number of biometric samples. It was calculated that for 40 users GAR was found to be 92%, 90%, 85% for degree of polynomial to be 3, 4 and 5 respectively. It was observed that increasing the degree of polynomial decreased the FAR rate, thus increasing the security

Instead of using the entire minutiae template to generate a protected fingerprint template, recently a non-invertible cancellable fingerprint construct based on a 3-5 minutiae pattern was proposed as a safer alternative. This paper investigates the recognition accuracy attainable by this new fingerprint construct. It is found that using five samples of a person's reference fingerprint and allowing for a maximum of three authentication attempts provides a genuine user with the best chance of being successfully authenticated. An evaluation of the FAR and FRR in this scenario demonstrates that the new fingerprint construct can be tuned to suit the performance and security requirements of different applications by adjusting the pattern size and matching thresholds. The fingerprint construct is then modified to improve its ability to discriminate between genuine users and impostors. Compared to other non-invertible fingerprint template protection schemes, the performance of the modified fingerprint construct is found to be favourable.

Quantizing real-valued templates into binary strings is a fundamental step in biometric compression and template protection. In this paper, we introduce the area under the FRR curve optimize bit allocation (AUF-OBA) principle. Given the bit error probability, AUF-OBA assigns the numbers of quantization bits to every feature, in such way that the analytical area under the false rejection rate (FRR) curve for a Hamming distance classifier (HDC) is minimized. Experiments on the FRGC face database yield good performances.

Multimodal biometric template protection (BTP) is gaining increasing attention as it overcomes the drawback of unimodal BTP. In this work, a token-less cancellable biometric scheme, namely Extended Feature Vector (EFV) Hashing, is applied to fuse the multimodal binary face and fingerprint template at a feature-level fusion. In advance to the unimodal EFV hashing, this work reorganizes the feature extension mechanism in EFV transformation and introduces the random sampling mechanism to increase the difficulty for reverse processing of the cancellable template. In addition, two fusion options are developed for producing the cancellable template. Experiments are conducted on the well-known Fingerprint FVC2004 and Face LFW datasets. The results demonstrate that the propose approach achieves a satisfactory verification rate with EER ~~ 0.1%.

Smartphone-based biometrics authentication has been increasingly used for many popular everyday applications such as e-banking and secure access control to personal services. The use of biometric data on smartphones introduces the need for capturing and storage of biometric data such as face images. Unlike the traditional passwords used for many services, biometric data once compromised cannot be replaced. Therefore, the biometric data not only should not be stored as a raw image but also needs to be protected such that the original image cannot be reconstructed even if the biometric data is available. The transforming of raw biometric data such as face image should not decrease the comparison performance limiting the use of biometric services. It can therefore be deduced that the feature representation and the template protection scheme should be robust to have reliable smartphone biometrics. This chapter presents two variants of a new approach of template protection by enforcing the structure preserving feature representation via manifolds, followed by the hashing on the manifold feature representation. The first variant is based on the Stochastic Neighbourhood Embedding and the second variant is based on the Laplacian Eigenmap. The cancelability feature for template protection using the proposed approach is induced through inherent hashing approach relying on manifold structure. We demonstrate the applicability of the proposed approach for smartphone biometrics using a moderately sized face biometric data set with 94 subjects captured in 15 different and independent sessions in a closed-set scenario. The presented approach indicates the applicability with a low Equal Error Rate, \(EER = 0.65\%\) and a Genuine Match Rate, \(GMR = 92.10\%\) at False Match Rate (FMR) of \(0.01\%\) for the first variant and the second variant provides \(EER = 0.82\%\) and \(GMR = 89.45\%\) at FMR of \(0.01\%\). We compare the presented approach against the unprotected template performance and the popularly used Bloom filter template.

Biometric template protection approaches have been developed to secure the biometric templates against image reconstruction on the stored templates. Two cancellable fingerprint template protection approaches namely minutiae-based bit-string cancellable fingerprint template and modified minutiae-based bit-string cancellable fingerprint template, are selected to be evaluated. Both approaches include the geometric information of the fingerprint into the extracted minutiae. Six modified fingerprint data sets are derived from the original fingerprint images in FVC2002DB1_B and FVC2002DB2_B by conducting the rotation and changing the quality of original fingerprint images according to the environment conditions during an emergency situation such as wet or dry fingers and disoriented angle of fingerprint images. The experimental results show that the modified minutiae-based bit-string cancellable fingerprint template performs well on all conditions during an emergency situation by achieving the matching accuracy between 83% and 100% on FVC2002DB1_B data set and between 99% and 100% on FVC2002DB2_B data set.

Security analysis and improvement of some biometric protected templates based on Bloom filters