Behaviour Biometrics Using AI for Continuous Authentication Systems

This chapter aims to enhance the security of textual passwords by adding a new layer that involves an individual's typing rhythm without requiring additional devices. It discusses authentication methods and develops a textual password authentication system, which takes advantage of the fact that every user has a distinct way of typing. Twenty participants, including novice and expert users, assessed the proposed system. The measuring metrics used were the False Acceptance Rate (FAR) and False Rejection Rate (FRR). The flight time and typing rhythm were the biometric identification template. The results indicated low false rejection and acceptance rates, with the initial session registering 0.0 FRR and 0.1 FAR. Two weeks later, the second session recorded 0.25 FRR and 0.0 FAR. Using this model, users do not need to select a complex password they might forget. Instead, they can utilize a good rhythm different from their natural typing rhythm, making it challenging to guess.

We examined the false acceptance rate (FAR) and false rejection rate (FRR) of varying precision verification experimental designs. Analysis of variance was applied to derive the subcomponents of imprecision (ie, repeatability, between-run, between-day imprecision) for complex matrix experimental designs (day × run × replicate; day × run). For simple nonmatrix designs (1 day × multiple replicates or multiday × 1 replicate), ordinary standard deviations were calculated. The FAR and FRR in these different scenarios were estimated. The FRR increased as more samples were included in the precision experiment. The application of an upper verification limit, which seeks to cap FRR at 5% for multiple experiments, significantly increased the FAR. The FRR decreases as the observed imprecision increases relative to the claimed imprecision and when a greater number of days, runs, or replicates are included in the verification design. Increasing the number or days, runs, or replicates also reduces the FAR for between-day imprecision and repeatability. Design of verification experiments should incorporate the local availability of resources and analytical expertise. The largest imprecision component should be targeted with a greater number of measurements. Consideration of both FAR and FRR should be given when committing a platform into service.

Session authentication schemes establish the identity of the user only at the beginning of the session, so they are vulnerable to attacks that tamper with communications after the establishment of the authenticated session. Moreover, smartphones themselves are used as authentication means, especially in two-factor authentication schemes, which are often required by several services. Whether the smartphone is in the hands of the legitimate user constitutes a great concern, and correspondingly whether the legitimate user is the one who uses the services. In response to these concerns, Behavioral Biometrics (BB) Continuous Authentication (CA) technologies have been proposed on a large corpus of literature. This paper presents a research on the development and validation of a BBCA system (named BioPrivacy), that is based on the user’s keystroke dynamics, using a Multi-Layer Perceptron (MLP). Also, we introduce a new behavioral biometrics collection tool, and we propose a methodology for the selection of an appropriate set of behavioral biometrics. Our system achieved 97.18% Accuracy, 0.02% Equal Error Rate (EER), 97.2% True Acceptance Rate (TAR) and 0.02% False Acceptance Rate (FAR).KeywordsMachine learningBehavioral biometricsContinuous authenticationMobile devicesMulti-layer perceptron (MLP)

The problem of speaker recognition from a given set of speakers for any language and any context is considered. A database of Russian numerals that contains speech segments from 216 men and 177 women, each of whom spoke from 400 to 800 words, is used for recognition. Speech has been recorded on different types of microphones in different rooms at the natural noise level. Recognition is based on solutions of the inverse problem of finding the voice excitation pulse shape for each pitch period by the known speech segment. The pulse shape is defined as the inverse Fourier transform of the regularized ratio of speech signal spectra at the intervals of the open and closed glottis. Recognition is carried out by ten parameters: the pitch period, the open glottis interval duration, times when the source amplitude is maximum, minimum, or zero, the amplitude ratio for the minimum and maximum source pulses, three decomposition ratios of the source function by the principal component method, and the vowel duration. In such a recognition procedure, in the case of the utterance of a word that contains one vowel, the false reject rate (FRR) for men is 1.7---5.4%, and the false acceptance rate (FAR) is 5.4---7.1%. For women FRR = 2---5.2% and FAR = 5.2---6.3%. The recognition error decreases with an increasing number of vowels in the speech signal. At 10 vowels, for men FRR = 0.05---0.2% and FAR = 0.07---0.8%, and for women FRR = 0.09---0.2% and FAR = 0.17---2.1%.

The cumulative match curve (CMC) is used as a measure of 1: m identification system performance. It judges the ranking capabilities of an identification system. The receiver operating characteristic curve (ROC curve) of a verification system, on the other hand, expresses the quality of a 1:1 matcher. The ROC plots the false accept rate (FAR) of a 1:1 matcher versus the false reject rate (FRR) of the matcher. We show that the CMC is also related to the FAR and FRR of a 1:1 matcher, i.e., the matcher that is used to rank the candidates by sorting the scores. This has as a consequence that when a 1:1 matcher is used for identification, that is, for sorting match scores from high to low, the CMC does not offer any additional information beyond the FAR and FRR curves. The CMC is just another way of displaying the data and can be computed from the FAR and FRR.

"This paper explores the application of neural networks in multimodal biometric authentication systems, emphasizing the integration of multiple biometric modalities to enhance security, accuracy, and robustness against various attacks. Traditional authentication methods, such as passwords and single-modal biometrics, often suffer from vulnerabilities, including spoofing, environmental factors, and data breaches. To address these challenges, multimodal authentication systems combine several biometric traits, such as facial recognition, fingerprint scanning, voice recognition, and keystroke dynamics, to achieve higher reliability and resistance to security threats. The study provides an overview of public datasets used for training neural network-based biometric authentication models, including VoxCeleb, RAVDESS, MOBIO, and SDUMLA-HMT. These datasets contain diverse biometric information necessary for developing robust multimodal authentication systems. The paper evaluates the effectiveness of existing approaches using key performance metrics such as accuracy, false acceptance rate (FAR), false rejection rate (FRR), and area under the curve (AUC). Additionally, specialized metrics are considered, including failure to enroll rate (FTE), failure to acquire rate (FTA), and template stability (TS), which are crucial for real-world applications. The role of neural networks in multimodal biometric authentication is analyzed by examining state-of-the-art architectures, including convolutional neural networks (CNNs) and deep learning-based feature fusion methods. Various fusion levels—feature-level, score-level, and decision-level—are discussed to determine the optimal integration strategy for improving authentication performance. The results indicate that multimodal systems significantly outperform unimodal authentication methods by reducing vulnerability to spoofing and environmental variations. Experimental findings suggest that integrating multiple biometric traits enhances the system’s adaptability to dynamic conditions, reducing both false acceptance and false rejection rates. Despite these advantages, several challenges remain, including computational complexity, data privacy concerns, and the need for real-time processing capabilities. Future research should focus on optimizing multimodal fusion techniques, improving generalization across different datasets, and enhancing the security of biometric templates against adversarial attacks. Additionally, developing lightweight neural network architectures suitable for mobile and embedded systems is essential for the practical deployment of multimodal authentication technologies"

Continuous authentication systems have been proposed as a promising solution to authenticate users in smartphones in a non-intrusive way. However, current systems have important weaknesses related to the amount of data or time needed to build precise user profiles, together with high rates of false alerts. Voice is a powerful dimension for identifying subjects but its suitability and importance have not been deeply analyzed regarding its inclusion in continuous authentication systems. This work presents the S3 platform, an artificial intelligence-enabled continuous authentication system that combines data from sensors, applications statistics and voice to authenticate users in smartphones. Experiments have tested the relevance of each kind of data, explored different strategies to combine them, and determined how many days of training are needed to obtain good enough profiles. Results showed that voice is much more relevant than sensors and applications statistics when building a precise authenticating system, and the combination of individual models was the best strategy. Finally, the S3 platform reached a good performance with only five days of use available for training the users’ profiles. As an additional contribution, a dataset with 21 volunteers interacting freely with their smartphones for more than sixty days has been created and made available to the community.

The main purpose of this study is to present a novel personal authentication approach with the electrocardiogram (ECG) signal. The electrocardiogram is a recording of the electrical activity of the heart and the recorded signals can be used for individual verification because ECG signals of one person are never the same as those of others. The discrete wavelet transform was applied for extracting features that are the wavelet coefficients derived from digitized signals sampled from one-lead ECG signal. By the proposed approach applied on 35 normal subjects and 10 arrhythmia patients, the verification rate was 100% for normal subjects and 81% for arrhythmia patients. Furthermore, the performance of the ECG verification system was evaluated by the false acceptance rate (FAR) and false rejection rate (FRR). The FAR was 0.83% and FRR was 0.86% for a database containing only 35 normal subjects. When 10 arrhythmia patients were added into the database, FAR was 12.50% and FRR was 5.11%. The experimental results demonstrated that the proposed approach worked well for normal subjects. For this reason, it can be concluded that ECG used as a biometric measure for personal identity verification is feasible.

Problem statement: In any real time biometric system processing speed and recognition time are crucial parameters. Reducing processing time involves many parameters like normalization, FAR, FRR, management of eyelid and eyelash occlusions, size of signature etc. Normalization consumes substantial amount of time of the system. This study contributes for improved iris recognition system with reduced processing time, False Acceptance Rate (FAR) and False Rejection Rate (FRR). Approach: To improve system performance and reliability of a biometric system. It avoided the iris normalization process used traditionally in iris recognition systems. The technique proposed here used different masks to filter out iris image from an eye. Comparative study of different masks was done and optimized mask is proposed. The experiment was carried on CASIA database consisting of 756 iris images of 108 persons. Each person contributes seven images of eye (108×7 = 756) images in the database. Results: In the proposed method: (1) Normalization step is avoided; (2) Computational time is reduced by 0.3342 sec; (3) Iris signature size is reduced; (4) Improved performance parameters. (With reduced feature size, proposed method achieves 99.4866% accuracy, 0.0069% FAR, 1.0198% FRR and significant increase in speed of the system). Conclusion: Iris signature proposed was comparatively small just of 1×24 size. Though Daugman’s method gives best accuracy of 99.90% but the iris signature length used by that algorithm is comparatively very high that is 1×2048 phase vector. Also Daugman has used phase information in signature formation. Our method gives a accuracy of 99.474% with a signature of comparatively very small length. This has definitely contributed to improve the speed.

We propose a novel modality for active biometric authentication: electrical muscle stimulation (EMS). To explore this, we engineered an interactive system, which we call ElectricAuth, that stimulates the user’s forearm muscles with a sequence of electrical impulses (i.e., EMS challenge) and measures the user’s involuntary finger movements (i.e., response to the challenge). ElectricAuth leverages EMS’s intersubject variability, where the same electrical stimulation results in different movements in different users because everybody’s physiology is unique (e.g., differences in bone and muscular structure, skin resistance and composition, etc.). As such, ElectricAuth allows users to login without memorizing passwords or PINs. ElectricAuth’s challenge-response structure makes it secure against data breaches and replay attacks, a major vulnerability facing today’s biometrics such as facial recognition and fingerprints. Furthermore, ElectricAuth never reuses the same challenge twice in authentications – in just one second of stimulation it encodes one of 68M possible challenges. In our user studies, we found that ElectricAuth resists: (1) impersonation attacks (false acceptance rate: 0.17% at 5% false rejection rate); (2) replay attacks (false acceptance rate: 0.00% at 5% false rejection rate); and, (3) synthesis attacks (false acceptance rates: 0.2-2.5%). Our longitudinal study also shows that ElectricAuth produces consistent results over time and across different humidity and muscle conditions.

Smartphones have recently seen massive growth in usage and become a repository for many types of personal information. The privacy and security are primary concerns for their usage, where there is a need to provide seamless and continuous authentication systems(CASs) for smartphones. We introduce in this work a proof-of-concept design and a case study for using a biologically-inspired and hardware-friendly CAS. Our proposed design adopts a hybrid Liquid State Machine (LSM) approach to perform automatic features extraction and multi-modal fusion scheme for users' interaction. Our work establishes the design concepts for future on-chip and explains why LSM can be a promising approach for fast, adaptive and reliable hardware CASs. The experimental part reveals our proof-of-concept testing results against the golden standard features. Furthermore, The results indicate a promising future for such design and a potential biologically-inspired CASs.

Among all biometric technologies, iris recognition is the most accurate and high confidence authentication system. Due to the limitations in PCA-based system, modified principal component analysis (PCA)-based feature extraction is proposed in iris recognition system. In the proposed system, features are extracted using Gaussian kernel PCA (GKPCA) and classified using support vector machine (SVM). GKPCA and SVM algorithms are evaluated using CASIA V3 iris database. The performances are compared with the existing PCA-based system. The proposed system achieves 96.67% of accuracy for 256 features using GKPCA linear SVM. False acceptance rate (FAR) and false rejection rate (FRR) are 0 and 3 respectively for linear SVM. The results show that the proposed system performs accurate localisation of patterns even in non-ideal conditions.

In this paper, we propose an approach to extract features of center of foot pressure (COP) obtained by a load distribution sensor and apply this method to develop a biometrics personal identification system. Biometrics technology, as a method of personal identification, plays an important role in our daily lives. In our experiment, we have a user stand on load distribution sensor with slipper, and acquire pressure data during a simple motion, as touching a bell nearby by one hand but without movements of feet. We propose a biometrics personal identification system with less information, time and low space. First, we calculate the site of COP from the obtained pressure data. Features for identification are extracted from the position and the movement of COP. Second, we built a k-out-of-n system and a neural network (NN) model with the feature parameter. Third, we input test data to the two systems. Finally, we give a comparison of these two methods. We employ 11 volunteers. The experimental result reveals that the proposed identification method can achieve an accuracy of 12.0% in FRR (False Rejection Rate) and 1.0% in FAR (False Acceptance Rate).

Biometric technology is considered as more effective technology for identification and recognition of individuals in most secure environments. Face recognition is a technique based on physiological biometric characteristics. In this paper, we propose Face Recognition using DT-CWT and LBP Features (FRDL) for different databases. The original face image is resized to uniform dimensions of 2 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sup> × 2 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">q</sup> . The five levels Dual-Tree Complex Wavelet Transform (DT-CWT) is applied on face image to obtain DT-CWT coefficients. The matrix of DT-CWT coefficients is segmented in to 3×3 matrixes. The Local Binary Pattern (LBP) algorithm is applied on each 3×3 matrix to get final features. The Euclidean Distance (ED) is used to compare features of test face image with data base images. It is observed that the values of False Rejection Rate (FRR), False Acceptance Rate (FAR) and Total Success Rate (TSR) are better in the proposed model compare to existing method.

While developing continuous authentication systems (CAS), we generally assume that samples from both genuine and impostor classes are readily available. However, the assumption may not be true in certain circumstances. Therefore, we explore the possibility of implementing CAS using only genuine samples. Specifically, we investigate the usefulness of four one-class classifiers OCC (elliptic envelope, isolation forest, local outliers factor, and one-class support vector machines) and their fusion. The performance of these classifiers was evaluated on four distinct behavioral biometric datasets, and compared with eight multi-class classifiers (MCC). The results demonstrate that if we have sufficient training data from the genuine user the OCC, and their fusion can closely match the performance of the majority of MCC. Our findings encourage the research community to use OCC in order to build CAS as they do not require knowledge of impostor class during the enrollment process.