Aniesha Alford

Genetic & Evolutionary Biometric Security: Disposable Feature Extractors for Mitigating Biometric Replay Attacks

Abstract Biometric-based access control systems (BACSs) are vulnerable to replay attacks. Replay attacks occur when a biometric template is intercepted and maliciously used to gain unauthorized access to a system. In this paper, we introduce a Genetic and Evolutionary Biometric Security (GEBS) application which uses a Genetic and Evolutionary Computation to develop disposable Feature Extractors (FEs) in an effort to mitigate replay attacks. We describe how a previously developed system known as GEFE (Genetic and Evolutionary Feature Extraction) can be used to evolve unique and disposable FEs for users of BACS. Furthermore, we propose two access control protocols based on the use of disposable FEs and/or their resulting templates (also referred to as feature vectors (FVs)). In our proposed protocols, FEs/FVs are used to authenticate the identity of individuals and are then discarded. Our results show that this GEBS application can be successfully used to mitigate biometric replay attacks.

A comparison of genetic feature selection and weighting techniques for multi-biometric recognition

In this paper, we compare genetic-based feature selection (GEFeS) and weighting (GEFeW) techniques for multi-biometric recognition using face and periocular biometric modalities. Our results show that fusing face and periocular features outperforms face-only and periocular-only biometric recognition. Of the two genetic-based approaches, GEFeW outperforms GEFeS.

Permutation-based biometric authentication protocols for mitigating replay attacks

A biometric replay attack occurs when a victims biometric information (in the form of a template) is stolen by a hacker as it is transmitted over a network and used by the hacker to impersonate the victim to gain unauthorized access. Biometric replay attacks can be particularly devastating because the victims of these attacks cannot easily alter their biometrics or the templates associated with their biometrics [1]. In an effort to mitigate biometric replay attacks, the authors of [2] proposed two biometric authentication protocols. These protocols are based on two principles: (a) it is possible to evolve a set of distinct feature extractors (FEs) and (b) distinct FEs produce distinct templates. These principles gave rise to the concept of disposable FEs (and templates). In this paper, we introduce two additional protocols based on disposable FEs and templates. Our results show that these new protocols can be used more efficiently than the two proposed in [2].

GEC-based multi-biometric fusion

In this paper, we use Genetic and Evolutionary Computation (GEC) to optimize the weights assigned to the biometric modalities of a multi-biometric system for score-level fusion. Our results show that GEC-based multi-biometric fusion provides a significant improvement in the recognition accuracy over evenly fused biometric modalities, increasing the accuracy from 90.77% to 95.24%.

Genetic and evolutionary methods for biometric feature reduction

In this paper, we investigate the use of Genetic and Evolutionary Computations (GECs) for feature selection (GEFeS), weighting (GEFeW), and hybrid weighting/selection (GEFeWS) in an attempt to increase recognition accuracy as well as reduce the number of features needed for biometric recognition. These GEC-based methods were first applied to a subset of 105 subjects taken from the Facial Recognition Grand Challenge (FRGC) dataset (FRGC-105) where several feature masks were evolved. The resulting feature masks were then tested on a larger subset taken from the FRGC dataset (FRGC-209) in an effort to investigate how well they generalise to unseen subjects. The results suggest that our GEC-based methods are effective in increasing the recognition accuracy and reducing the features needed for recognition. In addition, the evolved FRGC-105 feature masks generalised well on the unseen subjects within the FRGC-209 dataset.

A comparison of GEC-based feature selection and weighting for multimodal biometric recognition

In this paper, we compare the performance of a Steady-State Genetic Algorithm (SSGA) and an Estimation of Distribution Algorithm (EDA) for multi-biometric feature selection and weighting. Our results show that when fusing face and periocular modalities, SSGA-based feature weighting (GEFeWSSGA) produces higher average recognition accuracies, while EDA-based feature selection (GEFeSEDA) performs better at reducing the number of features needed for recognition.

Analyzing the cross-generalization ability of a hybrid genetic & evolutionary application for multibiometric feature weighting and selection

Genetic & Evolutionary Biometrics (GEB) is a new field of study devoted to the use of Genetic & Evolutionary Computations to solve some of the traditional problems within the field of biometrics. In this paper, we evaluate the performances of two GEB applications, Genetic & Evolutionary Fusion (GEF) and Genetic & Evolutionary Feature Weighting/Selection-Machine Learning (GEFeWS-ML), on the FRGC and MORPH databases. We then investigate the ability of the evolved weights and feature masks (FMs) to generalize across datasets. Our results showed that the GEB applications were robust, achieving high recognition accuracies across the datasets. In addition, the FMs achieved these recognition accuracies while using less than 50% of the originally extracted features.

Mitigating replay attacks using Darwinian-based Feature Extraction

In [1,2], a Genetic and Evolutionary Biometric Security (GEBS) application was presented for preventing biometric replay attacks. This technique used Genetic and Evolutionary Feature Extraction - Machine Learning (GEFEML) to create disposable feature extractors (FEs). These disposable FEs had higher recognition accuracy than a traditional feature extraction approach, known as the local binary pattern method. In [3], a two-stage process for developing FEs was developed. This technique is known as Darwinian Feature Extraction (DFE), and it created Darwinian FEs (dFEs) that had even higher recognition accuracy than GEFEML while maintaining a lower computational complexity. In this paper, we apply dFEs towards mitigating replay attacks and compare the results to disposable FEs using GEFEML. Our results show the effectiveness of GEFEML and DFE towards creating dFEs.

Genetic and evolutionary biometrics: Exploring value preference space for hybrid feature weighting and selection

Purpose – The aim of this paper is to explore the value preference space associated with the optimization and generalization performance of GEFeWSML.Design/methodology/approach – In this paper, the authors modified the evaluation function utilized by GEFeWSML such that the weights assigned to each objective (i.e. error reduction and feature reduction) were varied. For each set of weights, GEFeWSML was used to evolve FMs for the face, periocular, and face + periocular templates. The best performing FMs on the training set (FMtss) and the best performing FMs on the validation set (FM*s) were then applied to the test set in order to evaluate how well they generalized to the unseen subjects.Findings – By varying the weights assigned to each of the objectives, the authors were able to suggest values that would result in the best optimization and generalization performances for facial, periocular, and face + periocular recognition. GEFeWSML using these suggested values outperformed the previously reported GEFeW...

Genetic & Evolutionary Biometrics

Genetic & Evolutionary Computation (GEC) is the field of study devoted to the design, development, and analysis of problem solvers based on natural selection [1-4] and has been successfully applied to a wide range of complex, real world optimization problems in the areas of robotics [5], scheduling [6], music generation [7], aircraft design [1], and cyber secur‐ ity [8-11], just to name a few. Genetic and Evolutionary Computations (referred to as GECs) differ from most traditional problems solvers in that they are stochastic methods that evolve a population of candidate solutions (CSs) rather than just operating on a single CS. Due to the evolutionary nature of GECs, they are able to discover a wide variety of novel solutions to a particular problem at hand – solutions that radically differ from those developed by tradition‐ al problem solvers [3,12,13].