Template Protection Techniques Research Articles

A standard ranking algorithm for robust iris template protection

In iris biometric recognition systems, protecting the storage and transmission of iris templates is crucial, and template protection techniques are pivotal for ensuring their security. A prevalent approach involves using indexing methods as an effective algorithm for iris template protection, leveraging the index or rank of the extracted iris code to generate a secure iris template. Meantime, many privacy threats to biometric data have emerged, necessitating heightened protection measures. Specifically, protecting the privacy of iris data is imperative within the context of iris template protection during recognition processes. As stipulated by the international standard ISO/IEC 30136, effective iris template protection must concurrently meet the criteria of irreversibility, revocability, and unlinkability. Nevertheless, existing indexing methods on iris template protection faced the formidable challenge of simultaneously fulfilling these three privacy requirements while maintaining the efficacy of iris recognition. This paper introduces a standard ranking (standardR) algorithm, named standardR, designed to enhance the security of iris templates by transforming each iris template into an irreversible representation. The experimental results on the benchmarked Casia-Iris-interval dataset, along with two additional iris datasets MMU1 and UBRIS 1, demonstrate the efficacy of the proposed algorithm. The proposed standardR algorithm achieves an equal error rate (EER) of 0.1695% and an area under the curve of 0.93011% with the Casia-Iris-Interval dataset. Furthermore, the algorithm maintains efficient recognition with a reduced iris code length of 1280 bits, a time complexity of O(n log n), and satisfies the biometric template protection (BTP) requirements in irreversibility, unlinkability, and renewability.

Generation of Secure Fingerprint Template Using DFT for Consumer Electronics Devices

Biometric authentication systems are being extensively used to secure various applications. Consumer electronics devices also utilize biometrics as one of the authentication methods. However, this growth in the use of biometric based authentication may lead to the permanent loss of the biometric identity of a person if it is compromised, as biometric data cannot be changed. Hence, this poses the requirement of securing user templates in biometric based systems. In this paper, we propose a secure, alignment-free, and non-invertible fingerprint based user template protection technique which utilizes the mapping of pair-polar structures of minutiae in a 3D-grid and Discrete Fourier Transform (DFT). The proposed technique has been analyzed in terms of revocability, diversity, security, and performance by using four publicly available fingerprint databases of Fingerprint Verification Competition (FVC) 2002 and 2004. In addition to these databases, a partial fingerprint database generated from the FVC2002 DB1 is also utilized. The Equal Error Rate (EER) values of the proposed technique for all the databases are compared with that of the state-of-the-art techniques, and the superiority of the results depicts the robustness and effectiveness of the proposed technique.

A Secure Face Recognition for IoT-enabled Healthcare System

In Healthcare, the Internet of Things (IoT)-enabled surveillance cameras capture thousands of images every day, where face recognition provides reliable security as well as smart treatment through patient sentiment analysis, emotion detection, automated nurse calls, and hospital traffic systems. In this article, a secure face recognition system for the IoT-enabled Healthcare system has been proposed. Here each registered person will be identified by his/her face biometric with strong template protection schemes. To protect the biometric information, three-step template protection techniques are proposed: (i) Cancelable biometrics , (ii) BioCrypto-Circuit , and (iii) BioCrypto-Protection . The performance of the proposed system has been tested on four benchmark face databases, CVL, IITK, Casia-Face-v5, and FERET. The results of the proposed system are reported in terms of the correct recognition rate and the equal error rate. These performances have also been compared with some state-of-the-art methods with respect to each employed database, which shows the novelty of the proposed system.

A Study of Approaches and Measures aimed at Securing Biometric Fingerprint Templates in Verification and Identification Systems

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.

Cancelable Multibiometrics Template Security Using Deep Binarization and Secure Hashing

Template security and privacy is of utmost significance while designing a biometric system. Several biometric template protection systems have been presented in the past, but none of them have succeeded in striking a compromise between matching performance and security. This paper proposes a hybrid template protection technique for a multibiometric system based on deep binarization and secure hashing. The technique is employed at different stages of multibiometric fusion. In particular, the proposed technique of multibiometric fusion for template protection is tested using face and electrocardiogram (ECG) biometrics. The pre-trained deep CNN model utilizes transfer learning to analyze both the biometrics and prepare multimodal templates at different stages of biometric fusion e.g. sensors, features, and matchers. The templates obtained from different states of fusion are mapped to their corresponding classes, which are represented as binary codes that are unique and randomly generated. The binary codes are further encrypted for noninvertibility using a cryptographic hash, and thus the information of fused templates is hidden. Finally, hash codes are used to perform matching. The evaluation of the proposed technique using database for face (Multi-PIE) and ECG (PTB) biometrics reports high accuracy satisfying the requirements of unlinkability, cancelability, and irreversibility for template protection.

Adaptation of Pair-Polar Structures to Compute a Secure and Alignment-Free Fingerprint Template

The unalterable nature of fingerprint biometrics leads to permanent identity loss of a user if an original fingerprint template is compromised. Moreover, it is evident in the literature that reconstructing a fingerprint image from an original fingerprint template is a feasible task. In order to protect the fingerprint template, we propose a noninvertible and alignment-free fingerprint template protection technique by exploiting the pair-polar minutiae structures. In the proposed technique, a secure fingerprint template is generated in the form of a set of binary vectors. These vectors are computed from the many-to-one mapping of the transformed pair-polar coordinates into a 3-D grid. Results of the proposed technique are analyzed in terms of revocability, unlinkability, security, and performance on six publicly available databases of Fingerprint Verification Competition 2002 and 2004. The overall analysis of the results clearly shows the effectiveness of the proposed technique as compared to the existing state-of-the-art techniques.

Robust Authentication System with Privacy Preservation of Biometrics

IoT-based multi-biometric system is a blend of multiple biometric templates that can be used for user authentication/verification using sensors. The leakage of the biometric trait information may cause critical privacy and security issues. It is expected to protect the privacy details of individuals through the irreversibility, unlinkability, and renewability of multi-biometric templates used in the authentication system. This study presents a robust authentication system with secure multi-biometric template protection techniques based on discrete cosine transform feature transformation and Lagrange’s interpolation-based image transformation. Three biometric traits namely iris, fingerprint, and palm print are recorded using sensors to validate the proposed multi-biometric template protection system. The fusion of all traits used is giving an average of 95.42% genuine acceptance rate and an average of 4.57% false rejection rate. Despite any number of biometric templates used for authentication, the proposed image transformation techniques keep the size of the final storage requirement as 8 X 8, which achieves constant space complexity (O(1)). The stored template is not linked with original templates; it is irreversible and renewable as new enrolment of the same individual will produce a new template every time. Overall, the proposed technique provides a secure authentication system with high accuracy, a constant size database, and the privacy preservation of biometric traits.

Cancelable ECG biometric based on combination of deep transfer learning with DNA and amino acid approaches for human authentication

Recently, electrocardiogram (ECG) signals have received a high level of attention as a physiological signal in the field of biometrics. It has presented great possibilities for its strength against counterfeit. However, the ECG feature templates are irreplaceable, and a compromised template implies a permanent loss of identity. Therefore, several studies have been introduced biometric template protection techniques such as cancelable techniques to protect the original template in case it is stolen or lost. In this research, a cancelable ECG approach is proposed to protect the ECG feature template for human authentication. In our system, we first employed some image processing techniques for preprocessing the input ECG signals. Then, a deep transfer learning approach is employed to extract the deep ECG features. Later, the proposed cancelable approach based on DNA and amino acid is applied to protect the deep feature templates. Lastly, a Support Vector Machine (SVM) is employed for authentication. Extensive experiments on two commonly used datasets coupled with comprehensive theoretical analysis demonstrate the highest accuracy of the proposed system and the strong resilience of the system to various security and privacy attacks. Results show that the proposed cancelable method meets all requirements of cancelable biometrics such as irreversibility, revocability, and unlinkability.

Lightweight Bio-Chaos Crypt to Enhance the Security of Biometric Images in Internet of Things Applications

In recent times, numerous Internet of Things (IoT) applications have begun to use biometric identity for authentication purposes. The integrity and confidentiality of biometric templates during storage and transmission is crucial as it contains key information on the physical identity of the users. Encryption is an effective template protection technique. However, most of the edge side gadgets in the IoT environment require lightweight encryption schemes due to constraints in available power and memory space. Conventional cryptosystems are expensive because of their complexity and multiple rounds for encryption. In the present work, a lightweight bio-cryptosystem is developed to ensure security while storing and transmitting biometric templates. The proposed bio-crypto architecture has three stages—key generation, confusion and diffusion. A two-dimensional logistic sine map is used for key generation. A novel method of diffusion using DNA encoding and ciphering is proposed to decrease the complexity of the encryption process considerably and achieve desirable integrity. Simulations and security analysis indicate that the proposed cryptosystem has sufficient level of security and robustness, involves lesser computational complexity and has the potential of satisfying the requirements of IoT applications.

Alignment-free cancelable fingerprint templates with dual protection

Cancelable biometrics is an important biometric template protection technique. However, many existing cancelable fingerprint templates suffer post-transformation performance deterioration and the attacks via record multiplicity (ARM). In this paper, we design alignment-free cancelable fingerprint templates with dual protection, which is composed of the window-shift-XOR model and the partial discrete wavelet transform. The former defuses the ARM threat and is combined with the latter to provide dual protection and enhance matching performance. The designed cancelable templates meet the requirements of non-invertibility, diversity and revocability and demonstrate superior recognition accuracy, when evaluated over public databases; for example, the Equal Error Rate of the proposed method in the lost-key scenario under the 1vs1 protocol is 0% for both FVC2002 DB1 and DB2, 1.63% for FVC2002 DB3, 7.35% for FVC2004 DB1 and 4.69% for FVC2004DB2.

PolyCodes: generating cancelable biometric features using polynomial transformation

Cancelable biometrics is a template protection technique proposed to bridge the growing gap between ‘biometrics for security’ and ‘security for biometrics’. Various approaches have been reported in literature, yet transforming a biometric template for privacy preservation is a challenging task. The manuscript proposes a random polynomial based template transformation technique to generate protected biometric templates named as ‘PolyCodes’. These protected versions are privacy and discriminability preserving, revocable, and provide significant dimensionality reduction. Several polynomial functions with dimensionality reduction factor ranging from 65% to 90% are designed and evaluated for security and performance. Further, applicability of the proposed ‘PolyCodes’ is experimentally verified for many biometric modalities such as visible and thermal face, palmprint, palmvein, and fingervein.

Face template protection using deep LDPC codes learning

There is a noticeable tendency to apply deep convolutional neural network (CNN) in facial identification, since it is able to boost performance in face recognition and verification. However, due to the users have unique facial, exposure of face template to adversaries can severely compromise system security and users' privacy. Here, the authors propose a face template protection technique by using multi-label learning, which maps the facials into low-density parity-check (LDPC) codes. Firstly, a random binary sequence is generated to represent a user and further hashed to produce the protected template. During the training, the random binary sequences are encoded by an LDPC encoder to produce diverse binary codes. Based on carefully designed deep multi-label learning, the facial features of each user are mapped to a diverse binary code. In the process of recognition and verification, the deep CNN mapping architecture is modelled as a Gaussian channel, while the noise brought by intra-variations in the outputs of CNN can be removed by the LDPC decoder. Thus, a robust face template protection scheme is achieved. The simulation results on PIE and extended Yale B indicate that the proposed scheme achieves high genuine accept rate at 1% false accept rate.

Securing Stored Biometric Template Using Cryptographic Algorithm

The biometric template protection technique provides the security in many authentication applications. Authentication based on biometrics has more advantages over traditional methods such as password and token-based authentication methods. The advantage of any biometric-based authentication system over a traditional one is that the person must physically be present at that place while recognizing him. So, it is essential to secure these biometrics by combining these with cryptography. In the proposed algorithm, the AES algorithm is used for securing the stored and transmitted biometric templates using helping data. The helping data is a variable type of data which is changed at every attempt for registration. The final symmetric key AES algorithm is a combination of helping data and actual symmetric keys of the AES algorithm. The experimental analysis shows that a brute force attack takes a long time to recover the original biometric template from cipher biometric template. So, the proposed technique provides sufficient security to stored biometric templates.

3-Dimensional Secured Fingerprint Shell

Biometric systems relying on fingerprint usually use minutiae points information and store it directly in the database. However, databases are prone to get attacked by an adversary. As fingerprint can be generated using the information of its minutiae points, it is essential to ensure the security of the fingerprint data in biometric systems. Another problem associated with fingerprint authentication systems is the variation among fingerprint images of the same subject, which occurs due to rotation and translation of finger at the time of capturing fingerprints through sensors. A technique called Fingerprint Shell is proposed by Moujahdi et al. as a secured representation of fingerprint template. However, this technique uses only one intra-subject invariant feature, which is the distances between minutiae points and singular point to generate a 2-dimensional spiral curve which is used as a secured user template. In this paper, we analyze the weaknesses of the Fingerprint Shell and propose a highly secured fingerprint template protection technique in which a 3-dimensional spiral curve is generated as a secured user template for a fingerprint. To obtain the proposed secured fingerprint template, we utilize three intra-subject invariant features, namely distances between minutiae points and singular point, the orientation information of minutiae points and the ridge counts between minutiae points and singular point. Outcomes of the experimental analysis conducted on FVC (2000, 2002 and 2004) and IIT Kanpur databases show highly encouraging performance and exhibit the viability of the proposed technique. The technique has also been analyzed with respect to various attacks and is found to be highly secure and robust.

Random Projection-based Cancelable Template Generation for Sparsely Distributed Biometric Patterns

Cancelable biometrics, a template transformation approach, attempts to provide robustness for authentication services based on biometrics. Several biometric template protection techniques represent the biometric information in binary form as it provides benefits in matching and storage. In this context, it becomes clear that often such transformed binary representations can be easily compromised and breached. In this paper, we propose an efficient non-invertible template transformation approach using random projection technique and Discrete Fourier transformation to shield the binary biometric representations. The cancelable fingerprint templates designed by the proposed technique meets the requirements of revocability, diversity, non-invertibility and performance. The matching performance of the cancelable fingerprint templates generated using proposed technique, have improved when compared with the state-of-art methods.

A partial Hadamard transform approach to the design of cancelable fingerprint templates containing binary biometric representations

As an important biometric template protection technique, cancelable biometrics provides enhanced security for biometric-based authentication. Representing biometric information in binary form is useful in biometric template protection because it offers simplicity in feature representation and provides benefits in matching and storage. Therefore, it is no surprise that cancelable biometrics often exploits binary biometric representations as resultant templates. However, very often such binary biometric representations contained in cancelable biometrics have security shortfalls, because once they are compromised, the biometric features that they represent are likely to be retrieved. In this paper we propose an efficient non-invertible transformation – the partial Hadamard transform to securely protect binary biometric representations in the design of cancelable biometrics. When this non-invertible transform is applied to the DFT of the binary biometric representations, the resultant templates are complex vectors, from which the original binary vectors cannot be restored. A prominent feature of the proposed approach is that it preserves the stochastic distance between binary vectors after the transformation. This stochastic distance preserving property is theoretically proved and further demonstrated and verified by experiments. The cancelable fingerprint templates designed by the proposed partial Hadamard transform meet the requirements of revocability, diversity, non-invertibility and performance. Matching performance of the designed cancelable templates compares favorably with state-of-the-art methods that also involve binary biometric representations; for example, the Equal Error Rate of the proposed method in the lost-token scenario is 1% for FVC2002 DB1, 2% for FVC2002 DB2 and 5.2% for FVC2002 DB3.

Attacks on Biometric Systems: An Overview

Biometrics is a pattern recognition system that refers to the use of different physiological (face, fingerprints, etc.) and behavioral (voice, gait etc.) traits for identification and verification purposes. A biometrics-based personal authentication system has numerous advantages over traditional systems such as token-based (e.g., ID cards) or knowledge-based (e.g., password) but they are at the risk of attacks. This paper presents a literature review of attack system architecture and makes progress towards various attack points in biometric system. These attacks may compromise the template resulting in reducing the security of the system and motivates to study existing biometric template protection techniques to resist these attacks.

A Delaunay Quadrangle-Based Fingerprint Authentication System With Template Protection Using Topology Code for Local Registration and Security Enhancement

Although some nice properties of the Delaunay triangle-based structure have been exploited in many fingerprint authentication systems and satisfactory outcomes have been reported, most of these systems operate without template protection. In addition, the feature sets and similarity measures utilized in these systems are not suitable for existing template protection techniques. Moreover, local structural change caused by nonlinear distortion is often not considered adequately in these systems. In this paper, we propose a Delaunay quadrangle-based fingerprint authentication system to deal with nonlinear distortion-induced local structural change that the Delaunay triangle-based structure suffers. Fixed-length and alignment-free feature vectors extracted from Delaunay quadrangles are less sensitive to nonlinear distortion and more discriminative than those from Delaunay triangles and can be applied to existing template protection directly. Furthermore, we propose to construct a unique topology code from each Delaunay quadrangle. Not only can this unique topology code help to carry out accurate local registration under distortion, but it also enhances the security of template data. Experimental results on public databases and security analysis show that the Delaunay quadrangle-based system with topology code can achieve better performance and higher security level than the Delaunay triangle-based system, the Delaunay quadrangle-based system without topology code, and some other similar systems.

Masquerade attack on transform-based binary-template protection based on perceptron learning

With the increasing deployment of biometric systems, security of the biometric systems has become an essential issue to which serious attention has to be given. To prevent unauthorized access to a biometric system, protection has to be provided to the enrolled biometric templates so that if the database is compromised, the stored information will not enable any adversary to impersonate the victim in gaining an illegal access. In the past decade, transform-based template protection that stores binary one-way-transformed templates (e.g. Biohash) has appeared being one of the benchmark template protection techniques. While the security of such approach lies in the non-invertibility of the transform (e.g. given a transformed binary template, deriving the corresponding face image is infeasible), we will prove in this paper that, irrespective of whether the algorithm of transform-based approach is revealed, a synthetic face image can be constructed from the binary template and the stolen token (storing projection and discretization parameters) to obtain a highly-probable positive authentication response. Our proposed masquerade attack algorithms are mainly composed of a combination of perceptron learning and customized hill climbing algorithms. Experimental results show that our attack algorithms achieve very promising results where the best setting of our attack achieves 100% and 98.3% rank one recognition rates for the CMU PIE and FRGC databases correspondingly when the binarization algorithm (transformation plus discretization) is known; and 85.29% and 46.57% rank one recognition rates for the CMU PIE and FRGC databases correspondingly when the binarization algorithm is unknown.

Finger multibiometric cryptosystems: fusion strategy and template security

We address two critical issues in the design of a finger multibiometric system, i.e., fusion strategy and template security. First, three fusion strategies (feature-level, score-level, and decision-level fusions) with the corresponding template protection technique are proposed as the finger multibiometric cryptosystems to protect multiple finger biometric templates of fingerprint, finger vein, finger knuckle print, and finger shape modalities. Second, we theoretically analyze different fusion strategies for finger multibiometric cryptosystems with respect to their impact on security and recognition accuracy. Finally, the performance of finger multibiometric cryptosystems at different fusion levels is investigated on a merged finger multimodal biometric database. The comparative results suggest that the proposed finger multibiometric cryptosystem at feature-level fusion outperforms other approaches in terms of verification performance and template security.