Biometric Database Research Articles

Securing multimodal biometric template using local random projection and homomorphic encryption

Due to the rapid advancement of technology, biometrics is widely used in authenticating a person. The primary issue in biometric authentication is template protection, which protects the user’s privacy. To achieve this level of security, we transform the original template generated from the extracted features into a pseudo template. This paper considers two biometric traits, namely Iris and Fingerprint. First, the features are extracted from both the traits. After extracting the features, the feature vectors are compressed to reduce the size. Then the feature vectors of both the traits are fused. Later, local random projection (LRP) is applied to this template to build a revocable and un-linkable template. Finally, fully homomorphic encryption (FHE) is applied to this generated template to secure the user’s privacy, as all operations on the template are carried on encrypted data. Our proposed method improves the accuracy of the system as it generates rotational invariant codes. This proposed method is tested on the Children Multimodal Biometric Database (CMBD), which shows that our method can maintain user privacy with a good accuracy rate. Our method achieves an EER of 0.0214%.

Oceans, Archives, Perverts

This study follows the oceanic routes of female migrant laborers as a way to reconsider the geographies of queer theory through the colonial port city. In so doing, the author highlights feminized forms of migrant labor, including sex work and care work, as a central facet of the history of sexuality beyond the nation-state. This history begins in the 1920s and 1930s, when the League of Nations sponsored a massive investigation into international sex trafficking, through surveillance of port cities across the Atlantic, Indian, and Pacific Oceans. These investigations reveal the ways that female migrant laborers were constructed as nonnormative sexual subjects, both through their transient status as citizens and for performing reproductive labors outside the context of the white nuclear family. In this way, the league investigation offers an early case study for technologies attending to the biological specificity necessary to detain individuals at the border. This biometric archive lays the groundwork for a theorization of queer femininity, often ignored by historians of sexuality focused on the criminalization of sodomy. Through attention to an early biometric database, rather than criminal archives, what follows offers a geography of feminized labor and queer femininity based across a transoceanic network of port cities. A consideration of sex work in the midcentury novel, including Jean Rhys's Voyage in the Dark and J. G. Farrell's Singapore Grip, more closely establishes the biometric and aesthetic categories used to construct female sexual deviance at the midcentury.

Waiting for welfare: experiences of street traders from Delhi, India

ABSTRACT This article explores the nuances of the experiences of waiting for state-issued documents and state welfare. Waiting as an everyday experience forms an important aspect of the relationship between socio-economically marginalised groups and the state institutions. In order to examine this relationship, this paper draws upon eight interviews, conducted during December 2017 to February 2018 and in January 2019, among pheriwale. Pheriwale are self-employed traders, in Delhi, India, who collect huge amounts of second-hand/used-clothes and sell them forward to make a living. They largely work in highly precarious informal work environments, lack social security and depend on irregular income. However, as residents of India, they are also regulated through various state measures such as being registered within the national biometric database, as bank account holders and as recipients of public welfare provisions. By focusing on the experiences of pheriwale, findings show that waiting is shaped through intersecting hierarchies of gender, class and caste in the context of India. This article elucidates that a conceptualisation of waiting cannot overlook how the act of waiting for state-issued documents is tied into politics of recognition and redistribution.

Iris Liveness Detection Using Multiple Deep Convolution Networks

In the recent decade, comprehensive research has been carried out in terms of promising biometrics modalities regarding humans’ physical features for person recognition. This work focuses on iris characteristics and traits for person identification and iris liveness detection. This study used five pre-trained networks, including VGG-16, Inceptionv3, Resnet50, Densenet121, and EfficientNetB7, to recognize iris liveness using transfer learning techniques. These models are compared using three state-of-the-art biometric databases: the LivDet-Iris 2015 dataset, IIITD contact dataset, and ND Iris3D 2020 dataset. Validation accuracy, loss, precision, recall, and f1-score, APCER (attack presentation classification error rate), NPCER (normal presentation classification error rate), and ACER (average classification error rate) were used to evaluate the performance of all pre-trained models. According to the observational data, these models have a considerable ability to transfer their experience to the field of iris recognition and to recognize the nanostructures within the iris region. Using the ND Iris 3D 2020 dataset, the EfficeintNetB7 model has achieved 99.97% identification accuracy. Experiments show that pre-trained models outperform other current iris biometrics variants.

An improved Framework for Biometric Database’s privacy

Security and privacy are huge challenges in biometric systems. Biometrics are sensitive data that should be protected from any attacker and especially attackers targeting the confidentiality and integrity of biometric data. In this paper an extensive review of different physiological biometric techniques is provided. A comparative analysis of the various sus mentioned biometrics, including characteristics and properties is conducted. Qualitative and quantitative evaluation of the most relevant physiological biometrics is achieved. Furthermore, we propose a new framework for biometric database privacy. Our approach is based on the use of the promising fully homomorphic encryption technology. As a proof of concept, we establish an initial implementation of our security module using JAVA programming language.

A hybrid encryption framework based on Rubik’s cube for cancelable biometric cyber security applications

The need for high-speed and secure multi-biometric systems has grown in the last few decades. The progress in Internet applications and computer networks has prompted new problems with security and privacy. Having a reliable and secure means for storing biometrics is a necessary issue. Hence, data encryption and network security have become significant. Thence, because of the fast progress in network development, humans can easily and arbitrarily distribute or access digital data from networks. Therefore, ownership security has become a significant issue for individuals, and it requires much interest. Thus, there is a significant threat to copyright owners and digital multimedia producers to conserve multimedia from intruder prospection to avert loss in transmitted data. Ten years ago, most modern security systems depended on biometrics. Unfortunately, these systems have suffered for a long time from hacking trials. If the biometric databases have been hacked and stolen, the saved biometrics will be lost forever. Thus, there is a bad need to develop new cancelable biometric systems. In a classical authentication system, a user can easily change a password if it is compromised. However, the user’s biometrics are limited and unique, and if a user biometric is compromised, it will be impossible to change it in a particular system or at least difficult. Cancelable biometrics can be generated with intentional, repeatable distortions of biometric signals based on transforms. Hence, biometric templates are compared in the transform domain. Cancelable biometrics depend on transforming data to replace a single biometric template in the same or different systems. This paper presents a cancelable biometric system that depends on a novel hybrid encryption framework based on the Rubik’ cube technique. It allows simultaneous encryption of multiple images. The suggested hybrid enrollment stage begins with chaotic Baker map permutation in the Cipher FeedBack (CFB) operation mode, Advanced Encryption Standard (AES) or Ron's Code (RC6) algorithm as a first stage for encrypting the multiple images, separately. After that, the output encrypted images are passed to the second encryption stage via Rubik’s cube technique. Chaotic, RC6, or AES encrypted face images are utilized as the Rubik’s cube faces. For the RC6 and AES algorithms, they add a degree of diffusion, while the chaotic algorithm adds a degree of permutation. Moreover, the Rubik’s cube technique adds more permutations to the encrypted images, simultaneously. The encrypted images are used in the cancelable biometric system. The simulation results prove that the hybrid proposed encryption framework is efficient. Moreover, it has strong robustness and security.

Biometric masterkeys

Biometric authentication is used to secure digital or physical access. Such an authentication system uses a biometric database, where data are sometimes protected by cancelable transformations. This paper introduces the notion of biometric masterkeys. A masterkey is a feature vector such that the corresponding template matches with a significant number of templates stored in a cancelable biometric database. Such a masterkey is directly researched from a cancelable biometric database, but we also investigate another scenario in which the masterkey is fixed before the creation of the cancelable biometric database, providing additional access rights in the system for the masterkey’s owner. Experimental results are realized on three biometric databases: the fingerprint database FVC, the face image database LFW and the ECG database PTB. It shows the effectiveness and the efficiency of such masterkeys in both scenarios. In particular, from any given feature vector, we are able to construct a cancelable biometric database, for which the biometric template matches with all the templates of the database.

Cancelable electrocardiogram biometric system based on chaotic encryption using three‐dimensional logistic map for biometric‐based cloud services

AbstractBiometric features are extensively employed for security purposes, but they are vulnerable to threats and can be lost or compromised. Electrocardiogram (ECG) has been utilized as one of the most favorable biometrics. However, it contains confidential patient health information and personal identification details. Moreover, security flaws take place in hacking scenarios. Therefore, original biometrics must be secured by preventing them from being used in biometric databases. The enhanced security trend in biometric authentication is cancelable biometrics. Cancelable biometric systems can be built by generating regularly repeated distortions of biometric features to secure the sensitive data of the users. When cancelable features are disclosed, distortion parameters are modified, and new cancelable templates are generated. This paper presents a proposed cancelable ECG recognition system based on the 3D chaotic logistic map encryption, which has highly efficient random characteristics with confusion and diffusion properties. Normal and abnormal ECG signals have been used to test the proposed cancelable biometric recognition system, and good access results have been obtained. The results of the simulation indicate that the proposed system is secure, reliable, and practicable even with ECG signals for patients.

Signal‐level fusion for indexing and retrieval of facial biometric data

The growing scope, scale, and number of biometric deployments around the world emphasise the need for research into technologies facilitating efficient and reliable biometric identification queries. This work presents a method of indexing biometric databases, which relies on signal-level fusion of facial images (morphing) to create a multi-stage data structure and retrieval protocol. By successively pre-filtering the list of potential candidate identities, the proposed method makes it possible to reduce the necessary number of biometric template comparisons to complete a biometric identification transaction. The proposed method is extensively evaluated on publicly available databases using open-source and commercial off-the-shelf recognition systems. The results show that using the proposed method, the computational workload can be reduced down to around 30% while the biometric performance of a baseline exhaustive search-based retrieval is fully maintained, both in closed-set and open-set identification scenarios.

Биометрическая идентификация в Интернете: тенденции правового регулирования в России и за рубежом

The past few years saw the world's increased interest in biometric identification of Internet users. Biometric data differ from other identifiers: they are immutable and inalienable from their carriers, so any theft (including as a result of leakage) can lead to irreparable consequences. The aim of the article is to study the legal regulation of online biometric identification and processing of biometric data in the United States of America, China, and the European Union, as well as to assess the Russian legal regulation of this area in the light of world experience. For this, the authors use a comparative legal methodology. Each of the cases selected as research material illustrates one of the three regulatory models the authors identified. Each of the models is based on a certain constitutional concept of establishing a balance between users' private interests, on the one hand, and public interests, on the other. The US regulatory model is based on the establishment of minimum government guarantees of human rights observance in the processing of biometric data, while operators of Internet platforms remain with wide discretion in determining the procedure for processing biometric information. The Asian model, implemented, in particular, in China, proceeds from the priority of public interests over the privacy interests of individuals. States that implement such a model in their national legislation form centralized databases of subjects' biometric data, actively involving private Internet service providers in this process. The European model, which is based on the General Data Protection Regulation adopted in the European Union, on the contrary, proceeds from the recognition of the priority of the interests of the individual over public interests, establishing for this purpose strict rules regarding the processing of biometric data by Internet service providers and making it almost impossible to create centralized databases for accumulation of such information. Analyzing the trends in Russian legislation, the authors come to the conclusion that legal regulation in Russia tends to the Asian model and note that its implementation is associated with significant risks to human rights and freedoms, including in connection with data leaks from biometric databases. The emphasis is made on the fact that Russia, unlike Asian countries, is a member of the Council of Europe and is bound by the human rights standards laid down in its international documents. These standards should be taken into account when legislating in this area.

The use of civil biometric databases in criminal investigations: possible advances in the light of fundamental rights and guarantees

The use of civil biometric databases in criminal investigations: possible advances in the light of fundamental rights and guarantees

Preliminary biometric characteristics of Border Collies and their dependence on sport activity

<b>Biometric measurements were taken on 40 dogs of both sexes, 20 females and 20 males of Border Collies. Half of the population of each sex, i.e. 10 animals (active dogs), were either currently participating in dog frisbee competitions or had recently finished their sporting careers due to age. The other half (part) of the examined Border Collies, i.e. 10 females and 10 males, were animals that were not active in sports (non-active dogs). Most of the dogs came from Polish kennels but there were also Border Collies from other countries. The following measurements were taken: trunk length, height at withers, chest girth, fore limb (metacarpal) girth, thigh length, shank length, foot length and body weight. The collected results were processed statistically and indexes of trunk length, massiveness, eurysomia and boniness were calculated. It was found that Border Collie are characterized by some biometric traits (indexes) similar to Polish hunting dogs and Polish hounds and some of their indexes are also similar to the domestic breeds of Polish sheepdogs and Polish charts. Conducted biometric analysis showed only few, i.e. concerning height at withers of females and body weight of males statistically significant differences between examined groups of Border Collies. Consequently, there was no positive verification of the research hypothesis, which assumed that the value of traits and biometric indicators of Border Collie is different in jumping dogs in connection with their participation in various disciplines of dog competition. However, it can be assumed that for the needs of the developing sports cynology, there will be a need to select dogs with predispositions for athletic performance, and a useful tool to achieve this goal will be the analysis of biometric traits of dogs. The results of measurements collected in this study and the indices calculated on their basis also extend the biometric database of Border Collie dogs.

An improved Framework for Biometric Database’s privacy

Security and privacy are huge challenges in biometric systems. Biometrics are sensitive data that should be protected from any attacker and especially attackers targeting the confidentiality and integrity of biometric data. In this paper an extensive review of different physiological biometric techniques is provided. A comparative analysis of the various sus mentioned biometrics, including characteristics and properties is conducted. Qualitative and quantitative evaluation of the most relevant physiological biometrics is achieved. Furthermore, we propose a new framework for biometric database privacy. Our approach is based on the use of the promising fully homomorphic encryption technology. As a proof of concept, we establish an initial implementation of our security module using JAVA programming language.

К ВОПРОСУ ОБЕСПЕЧЕНИЯ БЕЗОПАСНОСТИ БИОМЕТРИЧЕСКИХ ДАННЫХ В ПЕРИОД ДИДЖИТАЛИЗАЦИИ ОБЩЕСТВА

The theme of the research is relevant since innovative technologies based on biometric data are widely introduced into the process of identification and verification of a person in the context of the digitalization of society. In addition, forensic biometric databases solve important tasks for personal identification of unidentified corpses, persons who have committed a crime, and persons on the wanted list. The need is noted for increasing the level of ensuring the protection of biometric personal data, in connection with the increasing cases of their loss or theft around the world. The research is aimed at investigating the meaning and classification of biometric data, highlighting the normative-legal acts regulating relations in the sphere of biometric information circulation, risks and threats to the security of biometric data. During the study, the methods of system-structural, comparative-legal and statistical analysis, formal-logical, general scientific and specific scientific methods of scientific knowledge were used. As a result of activities carried out based on a review of various approaches of domestic and foreign scientists and practitioners, the issues of using biometric information in various spheres of social life, as well as technical, organizational and legal aspects of ensuring the security of biometric data, are considered. The research results can be used in activities related to the circulation of biometric information, in forensic practice, during the classes in educational institutions and advanced training courses for forensic experts. Suggestions and recommendations are given for improving the level of ensuring the security of biometric databases, integrating various types of biometric modalities, systematic testing of biometric systems to protect against external unlawful influences.

Comparative Analysis of Feature Level Fusion Bimodal Biometrics for Access Control

The increasing quest for dependable, robust and secure recognition systems led to combining two or more biometric modalities for improved performance of a biometric system. Bimodal biometric systems have proven to achieve obvious advantages over unimodal systems in various applications such as access control, surveillance, forensics, deduplication and border control etc. In this study, a comparative analysis of combination of three biometric trait at feature level of fusion was carried out. Face, fingerprint and iris images were acquired from LAUTECH biometric database. The bimodal setup consists of face-iris, face-fingerprint and iris-finger modalities. Principal Component Analysis (PCA) was employed for feature extraction, weighted sum technique was used to fuse the images at feature level while Support Vector Machine (SVM) was used for classification. Experimental result revealed that the bimodal biometric achieved an improved performance than the unimodal biometric. The performances of the bimodal systems indicated that combination of face and iris features achieved the best performance with FAR, FRR and accuracy of 0.00%, 1.42% and 99.00% at 38.15 seconds. Hence, a bimodal face-iris recognition system would produce a more reliable security surveillance system for access control than other combination compared in this study.

Graph variational auto-encoder for deriving EEG-based graph embedding

Graph embedding is an effective method for deriving low-dimensional representations of graph data. The power of graph deep learning methods to characterize electroencephalogram (EEG) graph embedding is still in question. We designed a novel graph variational auto-encoder (GVAE) method to extract nodal features of brain functional connections. A new decoder model for the GVAEs network is proposed, which considers the node neighborhood of the reconstructed adjacency matrix. The GVAE is applied and tested on 3 biometric databases which contain 64 to 9 channels’ EEG recordings. For all datasets, promising results with more than 95% accuracy and considerably low computational cost are achieved compared to state-of-the-art user identification methods. The proposed GVAE is robust to a limited number of nodes and stable to users’ task performance. Moreover, we developed a traditional variational auto-encoder to demonstrate that more accurate features can be obtained when observing EEG-based brain connectivity from a graph perspective.

Biometric identity systems in law enforcement and the politics of (voice) recognition: The case of SiiP

Biometric identity systems are now a prominent feature of contemporary law enforcement, including in Europe. Often advanced on the premise of efficiency and accuracy, they have also been the subject of significant controversy. Much attention has focussed on longer-standing biometric data collection, such as finger-printing and facial recognition, foregrounding concerns with the impact such technologies can have on the nature of policing and fundamental human rights. Less researched is the growing use of voice recognition in law enforcement. This paper examines the case of the recent Speaker Identification Integrated Project, a European wide initiative to create the first international and interoperable database of voice biometrics, now the third largest biometric database at Interpol. Drawing on Freedom of Information requests, interviews and public documentation, we outline the emergence and features of SiiP and explore how voice is recognised and attributed meaning. We understand Speaker Identification Integrated Project as constituting a particular ‘regime of recognition’ premised on the use of soft biometrics (age, language, accent and gender) to disembed voice in order to optimise for difference. This, in turn, has implications for the nature and scope of law enforcement, people's position in society, and justice concerns more broadly.

The Appropriated Body: Biometrics Regime, The Digital State and Healthcare in Contemporary India

AbstractThe sheer size of the Indian population and its presence in a gigantic biometrics database has made possible the appropriation and control of millions of bodies on an everyday basis. It is being done at different levels by players operating the Digital State, with a markets‐based approach aiming to provide governance and development entitlements, healthcare being one among them. However, at the receiving end of this appropriative force are the 22 percent below poverty line (BPL) population, accounting for around 300 million people living at less than 1.25 dollars per day. These tend to be bodies facing a double jeopardy of historical‐social‐economic inequalities and negotiating the biometric means of accessing healthcare entitlements. Specifically, this refers to an arduous process of proving one's 'mistrusted' self to be able to enter the process of availing medical treatment. Based on qualitative fieldwork in Jharkhand and Delhi, the paper argues that the very process of biometrics‐based access to healthcare appropriates the bodies of BPL families even before they get any medical treatment. Findings reflect that the biometrics (technological) means for identifying the mistrusted bodies of BPL populations adds to the existing social inequalities.

DESIGN OF BIOMETRIC PROTECTION AUTHENTIFICATION SYSTEM BASED ON K-AVERAGE METHOD

The method of biometric identification, designed to ensure the protection of confidential information, is considered. The method of classification of biometric prints by means of machine learning is offered. One of the variants of the solution of the problem of identification of biometric images on the basis of the k-means algorithm is given. Marked data samples were created for learning and testing processes. Biometric fingerprint data were used to establish identity. A new fingerprint scan that belongs to a particular person is compared to the data stored for that person. If the measurements match, the statement that the person has been identified is true. Experimental results indicate that the k-means method is a promising approach to the classification of fingerprints. The development of biometrics leads to the creation of security systems with a better degree of recognition and with fewer errors than the security system on traditional media. Machine learning was performed using a number of samples from a known biometric database, and verification / testing was performed with samples from the same database that were not included in the training data set. Biometric fingerprint data based on the freely available NIST Special Database 302 were used to establish identity, and the learning outcomes were shown. A new fingerprint scan that belongs to a particular person is compared to the data stored for that person. If the measurements match, the statement that the person has been identified is true. The machine learning system is built on a modular basis, by forming combinations of individual modules scikit-learn library in a python environment.

Towards better and unlinkable protected biometric templates using label‐assisted discrete hashing

The growth of biometrics-based authentication in various services raises the need to protect biometric data at the storage level. Specifically, biometric templates need to be protected after features are extracted to avoid the leakage of biometric data and subsequent linkability issues. An approach based on discrete hashing is presented with the assistance of semantic labels to generate discriminative and privacy preserving protected templates in this work. The proposed approach can easily be adopted for a closed-enrolment set in which enrolment images are known a priori whereas the challenge of learning templates for a single subject remains open. To extend this approach for individual subject, the concept of auxiliary pseudouser enrolment data is introduced, through which a protected template can be generated at the user level. Through the use of a moderately sized multimodal biometric database of 94 subjects, the effectiveness of the proposed approach is illustrated to achieve a robust and secure template protection with irreversibility, unlinkability and renewability. With the set of experiments, the performance of the template protection approach is established and benchmarked against the popular bloom-filter technique. The proposed approach results in a high genuine match rate (≈100% at a false accept rate of 0.01%) and low equal error rate (EER ≈ 0%) and outperforms traditional approaches while satisfying other requirements of biometric template protection when the closed enrolment set is known. With auxiliary pseudousers, the performance of the proposed approach for user-level protected template creation results in an EER of 2.5%, indicating very low performance degradation compared with the known enrolment dataset. Along with the set of experimental validation of the proposed approach, a security analysis of the proposed approach is presented to demonstrate the unlinkability of the biometric templates using a state-of-art unlinkability metric.