Classifier ensembles and optimization techniques to improve the performance of cancellable fingerprint

Cancelable biometrics has been proposed for canceling and re-issuing biometric templates and for protecting privacy in biometrics systems. Recently, new cancelable biometric approaches are proposed based on BioHashing, which are random transformed feature-based cancelable biometrics. In this paper, we consider the accuracy of one of the cancelable biometrics based on BioHashing and face. Through this analysis, as an illustration, we would like to raise an issue to be considered in cancelable biometrics: accuracy may be traded for biometrics being cancelable.

Most current security and authentication systems are based on personal biometrics. The security problem is a major issue in the field of biometric systems. This is due to the use in databases of the original biometrics. Then biometrics will forever be lost if these databases are attacked. Protecting privacy is the most important goal of cancelable biometrics. In order to protect privacy, therefore, cancelable biometrics should be non-invertible in such a way that no information can be inverted from the cancelable biometric templates stored in personal identification/verification databases. One methodology to achieve non-invertibility is the employment of non-invertible transforms. This work suggests an encryption process for cancellable speaker identification using a hybrid encryption system. This system includes the 3D Jigsaw transforms and Fractional Fourier Transform (FrFT). The proposed scheme is compared with the optical Double Random Phase Encoding (DRPE) encryption process. The evaluation of simulation results of cancellable biometrics shows that the algorithm proposed is secure, authoritative, and feasible. The encryption and cancelability effects are good and reveal good performance. Also, it introduces recommended security and robustness levels for its utilization for achieving efficient cancellable biometrics systems.

Biometrics plays a vital role in security through authentication and verification. Securing the biometric template is the current challenge field of research. As intruders attack the biometric system which affects the applications which are being used for human authentication. To name a few border security, access control surveillance and so on. Vulnerabilities too affect the protected templates at the time of biometric verification process. Biometric templates can be protected by using the techniques like transformation or cancelable biometrics, biometrics cryptosystem, and hybridization. Most of the vulnerabilities or attacks are resolved by developing hybridization process like combining biometrics template with user knowledge keys or passwords for secure authentication. The challenges in template protection are like alignment of template, selection of pseudonymous identifiers (PI), and auxiliary data (AD). An attempt is made to review the literature in this direction and present few issues and challenges in the field of biometric template protection.

Cancelable biometric techniques play a vital role in the privacy and security of remote surveillance systems to keep the genuine users’ confidential data safe and away from intruders. This research presents an efficient cancelable biometric framework by exploiting an irreversible hybrid encryption technique that incorporates Deoxyribonucleic, Ribonucleic acid sequences (DNA and RNA), and the evolutionary optimization technique of the Genetic Algorithm (GA). So, these techniques are employed to create completely deformed templates from their original ones. Thus, our main contribution is offering a novel biometric security framework that achieves unique randomness characteristics using RNA and DNA sequences and the evolutionary GA-based encryption scheme. The proposed framework produces an entirely unrecognized biometric template by ciphering the main discriminative features of the biometric traits of the authorized clients. The proposed algorithm is first initialized by creating several encrypted biometric images of the original users by employing the logistic map function. Secondly, the initialized encrypted images are transformed into one vector of a binary array. Then, they are converted to their corresponding introns, exons, and consequently, their relevant codons are stored in the cloud database. Thirdly, these relevant codons are replaced by new ones after generating encrypted RNA lists. The utilized encryption key is extracted from the original biometric image after utilizing excessive permutations between its pixels. Then, the GA-based optimization technique is applied to select the most convenient biometric features. Finally, after employing the GA-based cross-over and mutation operations, the chosen features are used to generate the cancelable biometric traits. To validate the security efficacy of the proposed framework, different six biometric databases are used, which are Olivetti Research Laboratory (ORL) Faces (gray), CASIA v.5 Faces (color), UPOL Iris (gray), Indian Institute of Technology Delhi (IIT Delhi) Ear (color and gray), Fingerprint, and CASIA Palmprint (color and gray). The security performance of the proposed framework is compared to those of recent studies in this field, such as OSH (Optical Scanning Holography) and DRPE (Double Random Phase Encoding). The simulation results prove the superior performance of the proposed framework in terms of all tested evaluation metrics. The proposed framework provides high AROC (Area under the Receiver Operating Characteristic) that reaches 0.9990, low FAR (False Acceptance Rate) of 0.0015, more uniform histograms, high correlation values for genuine users, and complete hidden of biometric features. In addition, from a security perspective, the proposed framework accomplishes good entropy, UACI (unified average changing intensity), and NPCR (number of pixels change rate) values that reach 7.9960, 33.55%, and 99.65%, respectively.

In this paper, we propose a histogram of oriented gradient inspired cancelable biometrics - Random Augmented Histogram of Gradients (R∙HoG) for iris template protection. The proposed R∙HoG is built upon on two main components: 1) column vector random augmentation and 2) gradient orientation grouping mechanisms to transform the unaligned irisCode feature into the alignment-robust cancelable template. The alignment-robust property of the proposed R∙HoG enables the fast template comparison which is crucial for an efficient authentication process. Experiments were performed on CASIA-IrisV3-Internal and CASIA-IrisV4-Thousand datasets. The results demonstrate the proposed R∙HoG could achieve acceptable verification performance in both datasets. Other than that, the irreversibility and security properties are studied based on major security and privacy attacks in biometric system. Lastly, results from the benchmarking evaluation framework show the proposed method is satisfying the unlinkability property.

Rough set theory has proved efficient for many applications, including finding hidden patterns in data, data reduction, evaluating significance of data, and generating sets of decision rules from data. Recently, it has shown to be effective approach for constructing ensemble learning systems as well. Learning classifier systems are genetics-based machine learning techniques that have recently shown a high degree of competence on a variety of data mining problems. Attempts to improve its generalization capabilities in the literature using ensemble learning lack a systematic and robust techniques for partitioning the problem at hand. It is well known that ensemble performance depends on the problem decomposition technique being used. Rough set based learning classifier system ensemble is proposed in this paper. In this approach, rough set attribute reduction is used to generate a set of reducts, and then a diverse subset of these reducts is selected to train an ensemble of base classifiers. The experiments show that classification accuracy of reduct-based ensemble systems outperforms a single learning classifier system model. It has also shown better performance than either an ensemble of classifiers with all attributes being used or a single classifier trained by a single reduct. It has also shown competitive performance to the random subspace ensemble strategy on the set of real data sets used in the experiments.

Despite their usability advantages over traditional authentication systems, biometrics-based authentication systems suffer from inherent privacy violation and non-revocability issues. In order to address these issues, the concept of cancelable biometrics was introduced as a means of generating multiple, revocable, and noninvertible identities from true biometric templates. Apart from BioHashing, which is a two-factor cancelable biometrics technique based on mixing a set of tokenized user-specific random numbers with biometric features, cancelable biometrics techniques usually cannot preserve the recognition accuracy achieved using the unprotected biometric systems. However, as the employed token can be lost, shared, or stolen, BioHashing suffers from the same issues associated with token-based authentication systems. In this paper, a reliable tokenless cancelable biometrics scheme, referred to as BioEncoding, for protecting IrisCodes is presented. Unlike BioHashing, BioEncoding can be used as a one-factor authentication scheme that relies only on sole IrisCodes. A unique noninvertible compact bit-string, referred to as BioCode, is randomly derived from a true IrisCode. Rather than the true IrisCode, the derived BioCode can be used efficiently to verify the user identity without degrading the recognition accuracy obtained using original IrisCodes. Additionally, BioEncoding satisfies all the requirements of the cancelable biometrics construct. The performance of BioEncoding is compared with the performance of BioHashing in the stolen-token scenario and the experimental results show the superiority of the proposed method over BioHashing-based techniques.

Cancelable biometrics are a group of techniques to transform the input biometric to an irreversible feature intentionally using a transformation function and usually a key in order to provide security and privacy in biometric recognition systems. This transformation is repeatable enabling subsequent biometric comparisons. This paper introduces a new idea to be exploited as a transformation function for cancelable biometrics aimed at protecting templates against iterative optimization attacks. Our proposed scheme is based on time-varying keys (random biometrics in our case) and morphing transformations. An experimental implementation of the proposed scheme is given for face biometrics. The results confirm that the proposed approach is able to withstand leakage attacks while improving the recognition performance.

Trivial quantisation is widely used in cancellable biometrics and bio-cryptosystems for error tolerance. This method segments the feature domain into several non-overlapping intervals of equal size, whereas all features in the same interval will be considered matched. Although it is intuitive that trivial quantisation brings about the boundary issue, similar features near interval boundaries may be mapped into different intervals and lead to matching failure. Previous works do not provide specific theoretical analysis on how trivial quantisation impacts discrimination power (DP), an important performance index in biometric systems. Assuming genuine features and imposter features follow Gaussian distributions, the DP provided by the conventional matching method and trivial quantisation-based matching method from a theoretical perspective is discussed and compared. Also, formulas are developed for calculating the error tolerance parameter that maximises the DP in each method and the discrimination loss caused by trivial quantisation.

Distinguish self- and hetero-perceived stress through behavioral imaging and physiological features

Brain Computer Interfaces allow the interaction between a person and their environment using signals extracted directly from the brain. One of the most common non-invasive methods of brain signal acquisition is the electroencephalography (EEG). An EEG based BCI system generally involves four steps: preprocessing, feature extraction, feature selection, and classification. In order to design a real applicable BCI system, it is important to provide: good classification performance, adequate computational cost, robustness to variations of the signal between trials and between subjects, and a classifiers model that cope with highly dimensional data. Ensemble of classifiers is a learning model that, with a proper design, can satisfy those conditions, which make them a good match for a BCI application. In this paper, some ensemble of classifiers designs are evaluated and compared with other BCI approaches on three different subjects. In the proposed model, Genetic Algorithm is employed as feature selection method and Wavelet Packet Decomposition as preprocessing procedure. Four fusion methods were applied in the ensembles design, including: Majority Voting, Weighted Majority Voting, Genetic Algorithm for classifier selection and Genetic Algorithm to compute the weights for the Weighted Majority fusion method. The best results were obtained with the Weighted Majority Voting fusion method based on Genetic Algorithm.

A lightweight machine learning-based authentication framework for smart IoT devices

Biometric systems use personal biological or behavioural traits that can uniquely characterise an individual but this uniqueness property also becomes its potential weakness when the template characterising a biometric trait is stolen or compromised. To this end, we consider two strategies to improving biometric template protection and performance, namely, (1) using multiple privacy schemes and (2) using multiple matching algorithms. While multiple privacy schemes can improve the security of a biometric system by protecting its template; using multiple matching algorithms or similarly, multiple biometric traits along with their respective matching algorithms, can improve the system performance due to reduced intra-class variability. The above two strategies lead to a novel, ensemble system that is derived from multiple privacy schemes. Our findings suggest that, under the worst-case scenario evaluation where the key or keys protecting the template are stolen, multi-privacy protection scheme can outperform a single protection scheme as well as the baseline biometric system without template protection.

Ambient Intelligence represents the medium with a huge number of connected heterogeneous and dynamic devices that respond to the presence of people. The development and implementation of technologies to ensure the security and reliability of such systems is the main task of many studies in this direction. One of the important technologies for the formation of a secure Ambient Intelligence is biometric systems. Biometric systems represent techniques for describing and measuring personal unique physiological and behavioral characteristics of a person and methods for applying them to automatic identification or authentication processes. In this paper, the basic principles and algorithms of a biometric identification system based on iris recognition are considered. The purpose of the research is to determine the structure of the security systems of Ambient Intelligence using biometric technologies.

The connection between emotional states and physical health has attracted widespread attention. The emotional stress assessment can help healthcare professionals figure out the patient's engagement toward the diagnostic plan and optimize the rehabilitation program as feedback. It is of great significance to study the changes of physiological features in the process of emotional change and find out subset of one or several physiological features that can best represent the changes of psychological state in a statistical sense. Previous studies had used the differences in physiological features between discrete emotional states to select feature subsets. However, the emotional state of the human body is continuously changing. The conventional feature selection methods ignored the dynamic process of an individual's emotional stress in real life. Therefore, a dedicated experimental was conducted while three peripheral physiological signals, i.e., ElectroCardioGram (ECG), Galvanic Skin Resistance (GSR), and Blood Volume Pulse (BVP), were continuously acquired. This paper reported a novel feature selection method based on emotional state transition, the experimental results show that the number of physiological features selected by the proposed method in this paper is 13, including 5 features of ECG, 4 features of PPG and 4 features of GSR, respectively, which are superior to PCA method and conventional feature selection method based on discrete emotional states in terms of dimension reduction. The classification results show that the accuracy of the proposed method in emotion recognition based on ECG and PPG is higher than the other two methods. These results suggest that the proposed method can serve as a viable alternative to conventional feature selection methods, and emotional state transition deserves more attention to promote the development of stress assessment.