Neuromorphic Hardware Accelerated Adaptive Authentication System

A sole biometric identifier in construction an individual identification is often not able to meet the preferred performance requirements. Biometric identification pedestal on multiple biometrics correspond to an up-and-coming trend. computerized biometric scheme for person identification gauge a “signature” of the human body, compare the resulting characteristic to a database, and cause to be an request dependent decision. These biometric systems for personal authentication and identification are based upon physiological or behavioral features which are classically characteristic, even though point in time varying, such as Face recognition, Iris recognition, Fingerprint verification, Palm print verification in making a personal identification. Multi-biometric systems, which consolidate in sequence from multiple biometric sources, are in advance popularity since they are able to conquer limitations such as non-universality, noisy sensor data, large intra-user difference and vulnerability to spoof attacks that are commonly encountered in uni-biometric systems. In this paper, it addresses the concept issues and the applications strategies of multi-biometric systems.

This paper considers various personal identification systems based on questions and answers concerning knowledge inherent to the individual, and discusses the personal identification probability. Assume a personal identification system which contains N knowledge items and assume that a solver has forgotten the correct answers for M items after the registration. The behavior of the system is as follows: Q knowledge items for questions are selected randomly from N items. For each of the selected items, R selection keys are presented which include a correct answer and the solver is requested to select one. When the solver forgets the correct answer, the probability of correct answer is 1/R; otherwise it is 1. The following three systems are considered under such conditions. System I decides the solver as correct if all answers to the extracted Q items are correct. System II decides the solver as correct if there are fewer than K incorrect answers. System III decides the solver as correct unless k or more consecutive answers are incorrect. It is seen that the probability of personal identification increases in the order of I, II and III. It is not always true that the probability of excluding an incorrect solver is low if the probability of personal identification is high. Each of the considered systems is suited to particular applications, depending on the environment.

With the ubiquity of handwriting in everyday tasks, it is surprising that existing avenues for handwriting authentication remain largely out of reach for the average individual or organization. Current solutions often rely on expensive or specialized equipment, and most existing research focuses on signatures rather than freeform handwriting. This limits the applicability of such technology to a narrow range of scenarios. In this paper, we argue that wearable devices might make handwriting authentication scalable and affordable. We design and evaluate two wearables-driven freeform handwriting authentication systems, one centered on a deep neural network and the other using human-engineered features. Our authentication systems are thoroughly tested across three writing experiments (involving 53 participants) that were carefully mapped to typical writing scenarios. We show the best performing configuration to attain an equal error rate of 5.51%, suggesting the potential of this modality for use in a multi-modal authentication system. To evaluate how our authentication systems perform against attacks by determined attackers, we developed and evaluated two impostor attacks that correspond to highly likely attack vectors. We then show that certain authentication system configurations are resistant to the attack. This paper represents an important step toward consumer ready wearables-driven freeform handwriting authentication.

This paper presents an intelligent system for person identification with biometric measures such as signature, fingerprint and face. We describe the neural network architectures used to achieve person identification based on the biometrics measures. Simulation results show that the proposed method provides good recognition.

"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"

This paper presents the iris recognition system for biometric personal identification using neural network. Personal identification consists of localization of the iris region and generation of a data set of iris images followed by iris pattern recognition. In this paper, a fast algorithm is proposed for the localization of the inner and outer boundaries of the iris region. Located iris is extracted from an eye image, and, after normalization and enhancement, it is represented by a data set. Using this data set a Neural Network (NN) is used for the classification of iris patterns. The adaptive learning strategy is applied for training of the NN. The results of simulations illustrate the effectiveness of the neural system in personal identification.

A Multimodal authentication system with fusion at decision level employing Iris and Finger Vein is developed. This paper also proposes a novel feature extraction technique for finger vein and iris traits. This approach combines the decisions from the individual modalities using the conventional AND rule. Experimental results demonstrate the effectiveness of the proposed multimodal authentication system for accurate person authentication.

In this paper an improved face detection method based on our previous Information-Based Maximum Discrimination approach is presented that maximizes the discrimination between face and non-face examples in a training set without even using color or motion information. A short review of our previous method is given together with the description of the intuition behind and our recent improvement on its detection speed. A person identification system has been developed that performs multi-modal person identification in real-time video based on this newly improved face detection method together with speaker identification.

This paper investigates the potential of surface electromyography (sEMG) as a new biometric modality and proposes a deep neural network architecture as the backbone of a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">gesture-independent</i> personal identification system. The paper focuses on the real-world translation of such a model through systematic optimization, which finds the minimum number of gestures and sensors needed for training. Focusing on “dynamic sEMG”, our proposed method can successfully identify 40 subjects with an average accuracy of 97%. This is achieved when gestures are the same in training, validation, and testing (the subjects need to repeat a particular gesture among a set of seven known gestures as a passcode). In a more complex scenario, when training gestures differ from those in validation and testing, our model can achieve an average accuracy of 90%, demonstrating that the proposed model can extract the unique patterns to identify a user regardless of gestures. Taking advantage of Gradient-weighted Class Activation Mapping (Grad-CAM), we explore the attention of the model on segments of the spectrotemporal space of the input signals. Grad-CAM not only sheds light on sEMG-based personal identification by decoding and visualizing the unique user-specific neurophysiological pattern but also generates a two-dimensional spectrotemporal mask used to reduce the model complexity significantly. As a result of the systematic optimization and Grad-CAM analysis, our proposed identification method needs only 4% of data for training, boosting practicality. This paper also reveals the robustness of the proposed model for cross-day evaluation. Finally, the comparative study shows the superiority of our proposed model over several state-of-the-art algorithms.

The heart electrical activity has highly distinctive characteristics for each individual, which motivated us to use the electrocardiogram signal (ECG) as a biometric characteristic. This paper presents a new approach for human recognition from their Electrocardiograms (ECG). The proposed approach is based on an extraction feature with fiducial detection in time domain. It consists of three steps. After the preprocessing step, we extracted ten morphological descriptors and sixty hermite Polynomials Expansion coefficients (HPEc) from each heartbeat which represented the second step. The classification step is done by using a binary SVM and the hidden Markov model (HMM). In this step, a particular strategy of persons' identification was adopted: Firstly, we used four groups of morphological descriptors separately. Secondly, we combined them in one input vector of our classification system. Moreover, we employed the hermite Polynomials Expansion coefficients apart. In order to improve performance, we associated the HPEc with all groups of morphological descriptors as input parameters of our classification system. We tested our algorithm on 18 healthy signals of the MIT_BIH database. The results of experiments showed that the proposed hybrid approach has achieved an identification rate equal to 98.97% using SVM and 99.02% using HMM.

Social games offer a rich and challenging environment to develop and evaluate complex robot behaviors. Social interactions with robots benefit from personalization, which requires person identification—a process that raises privacy concerns. Soft biometrics, however, offer a privacy-preserving alternative by enabling short-term identification without relying on private or sensitive features. In this work, we leverage a zero-shot Visual Question Answering (VQA) person identification system and adapt it to make Pepper play Guess Who? The identification module performance is firstly studied offline in the AveRobot dataset. Afterwards, it is integrated in a ROS based architecture that manages the game flow and enables natural verbal interaction. Experiments conducted with 29 subjects demonstrate that the system achieves identification performance nearly equivalent to that of hard biometric-based systems while also offering engaging and entertaining gameplay. Notably, user feedback reveals a high level of acceptance, highlighting that social gaming with robots is a promising avenue for developing and testing complex behaviors.

A real-time automatic personal identification system should meet the conflicting dual requirements of accuracy and response time. In addition, it also should be user-friendly. We introduce a medium-size realtime automatic personal identification system, F2ID, which integrates faces and fingerprints to make a personal identification. F2ID overcomes some of the limitations of face recognition systems and fingerprint verification systems and can achieve a desirable identification accuracy with a tolerable response time. We have tested our system on a limited set of face and fingerprint images collected in a laboratory environment. Experimental results show that that our system meets both the identification accuracy as well as the speed requirements.

The importance of automatic person identification using non-intrusive biometric modality has created enormous interest in computer vision society over the last few years. For this, gait based person recognition is receiving much more attention in different applications like visual surveillance, security control, people counting. In this paper, we have presented a gait based person identification system using 3D human pose modeling for any arbitrary walking pattern in any unrestricted indoor environment, using Microsoft Kinect sensor. Instead of estimating gait cycle, we have modeled the gait pattern with a spatiotemporal set of key poses and sub-poses which occur periodically in different gait cycles. The robustness of the solution is increased by outlier detection to handle noisy skeleton data obtained from Kinect. The performance of the proposed system is also assessed with rotating Kinect setup to increase the field of view of single Kinect. We have done the average and worst case performance evaluation of the system with respect to the existing Kinect based approaches. It needs to be mentioned that our proposed person identification system is able to achieve a frame level F-score of more than 90% for 20 subjects with fixed Kinect setup.

Authentication Systems Using ID Cards over NFC Links: The Spanish Experience Using DNIe

Advancement of information technology coupled with the need for high security for passwords, the application of biometric as identification and recognition process serves a crucial purpose to avoid the risk to find or still. The texture pattern produces by hand geometry for authenticated access control it is the true substitute for passwords and identifiers in converse with the existing method biometric traits i.e. fingerprint and knuckle multimodal authentication system utilize line texture pattern to achieve actual personal identification. In this paper, we proposed the authentication system which uses multimodality feature extraction techniques with neural network as a classifier. Knuckle is a quite unique biometric trait having inherent skin pattern combined with fingerprint to implement multimodality. The performance of the system has been tested on biometric database that includes 16 subject's hands. The experimental result shows that multimodality features based authentication system has better authentication rate over single feature.