Continuous Authentication Research Articles

Intelligent solution for automatic online exam monitoring

<p><span lang="EN-US">E-learning has shown significant growth in recent years due to its unavoidable benefits in unexpected situations such as the coronavirus disease 2019 (COVID-19) pandemic. Indeed, online exam is a very important component of an online learning program. It allows higher education institutions to assess student learning outcomes. However, cheating in exams is a widespread phenomenon worldwide, which creates several challenges in terms of integrity, reliability and security of online examinations. In this study, we propose a continuous authentication system for online exam. Our intelligent inference system based on machine learning algorithms and rules, detects continuously any inappropriate behavior in order to limit and prevent fraud. The proposed model includes several modules to enhance security, namely the registration module, the continuous students’ identity verification and control module, the live video stream and the end-to-end sessions recording.</span></p>

A novel continuous authentication method using biometrics for IOT devices

In this paper, we examine continuous authentication for IoT devices using real-time biometrics of a person's electrocardiogram (ECG) and electromyography (EMG). ECG is mainly used as a biometric identifier because it has specific features such as mathematical, morphological, and wavelet characteristics. EMG is a bio-signal defining a hand gesture of a person. Our authentication system would require no human interaction as it will have a continuous authentication schema. As soon as the user leaves a specific perimeter, the session will be killed by the system. In this paper, we propose a challenging and integrated methodology for developing, prototyping, and evaluating a continuous authentication scheme to ensure that currently insecure IoT networks are improved to have a high level of security with two layers of biometric security with continuous authentication to perform authentication in an automated manner. We used the dataset from PhysioNet for ECG, which contains samples of around 12 K for 298 people. We also used the EMG dataset available on the geostatic python library containing 150 K samples. In this experiment, we concluded that it is viable to use our continuous authentication for IoT devices with the lowest performance consumption and power consumption. The experimentation also demonstrates that the training model on two bio-signals helps obtain higher accuracy on continuous authentication within an average of 99.6%-99.99%. Our authentication schema can be implemented and integrated on any IoT device with having at least one wireless frequency that can receive and send a signal to the sender/authenticator.

A feasibility study on using EEG for Biometric Trait Authentication System

Abstract The neuronal activity has a unique genetic signature that can be used for personal identification and authentication. Continuous authentication of individuals is required in the field involving high security, such as military services, intelligence organizations and secret agencies. Electroencephalogram (EEG) based authentication method is favorable due to its uniqueness and the fact that it can be used even when the person is unconscious. In this study, we investigated the number of samples per subject required to reliably develop a biometric trait authentication system. Initially, we extracted the background EEG signals from the publicly available Temple University Hospital (TUH) database. A total of 46 statistical and frequency domain features were extracted from each EEG signal per subject. The classification was performed using the extreme Gradient Boosting (XGBoost) classifier. We varied the number of EEG signal segments per subject from 5 to 127 with an increment of 5 segments per trial. Finally, the performance parameters such as accuracy, sensitivity, specificity, precision and F-measure were obtained in each case for the biometric authentication system using the test data. Our model achieved the highest accuracy of 100% when more than 75 EEG signals per subject were considered for the analysis. We also identified alpha band power as the most efficient feature for authentication. Our results show that EEG signals can be effectively used for personal identification and authentication.

Fourier Synchrosqueezing Transform-ICA-EMD Framework Based EOG-Biometric Sustainable and Continuous Authentication via Voluntary Eye Blinking Activities.

In recent years, limited works on EOG (electrooculography)-based biometric authentication systems have been carried out with eye movements or eye blinking activities in the current literature. EOGs have permanent and unique traits that can separate one individual from another. In this work, we have investigated FSST (Fourier Synchrosqueezing Transform)-ICA (Independent Component Analysis)-EMD (Empirical Mode Decomposition) robust framework-based EOG-biometric authentication (one-versus-others verification) performances using ensembled RNN (Recurrent Neural Network) deep models voluntary eye blinkings movements. FSST is implemented to provide accurate and dense temporal-spatial properties of EOGs on the state-of-the-art time-frequency matrix. ICA is a powerful statistical tool to decompose multiple recording electrodes. Finally, EMD is deployed to isolate EOG signals from the EEGs collected from the scalp. As our best knowledge, this is the first research attempt to explore the success of the FSST-ICA-EMD framework on EOG-biometric authentication generated via voluntary eye blinking activities in the limited EOG-related biometric literature. According to the promising results, improved and high recognition accuracies (ACC/Accuracy: ≥99.99% and AUC/Area under the Curve: 0.99) have been achieved in addition to the high TAR (true acceptance rate) scores (≥98%) and low FAR (false acceptance rate) scores (≤3.33%) in seven individuals. On the other hand, authentication and monitoring for online users/students are becoming essential and important tasks due to the increase of the digital world (e-learning, e-banking, or e-government systems) and the COVID-19 pandemic. Especially in order to ensure reliable access, a highly scalable and affordable approach for authenticating the examinee without cheating or monitoring high-data-size video streaming is required in e-learning platforms and online education strategies. Hence, this work may present an approach that offers a sustainable, continuous, and reliable EOG-biometric authentication of digital applications, including e-learning platforms for users/students.

Privacy-preserving continuous authentication using behavioral biometrics

Continuous authentication modalities collect and utilize users’ sensitive data to authenticate them continuously. Such data contain information about user activities, behaviors, and other demographic information, which causes privacy concerns. In this paper, we propose two privacy-preserving protocols that enable continuous authentication while preventing the disclosure of user-sensitive information to an authentication server. We utilize homomorphic cryptographic primitives that protect the privacy of biometric features with an oblivious transfer protocol that enables privacy-preserving information retrieval. We performed the biometric evaluation of the proposed protocols on two datasets, a swipe gesture dataset and a keystroke dynamics dataset. The biometric evaluation shows that the protocols have very good performance. The execution time of the protocols is measured by considering continuous authentication using: only swipe gestures, keystroke dynamics, and hybrid modalities. The execution time proves the protocols are very efficient, even on high-security levels.

SearchAuth: Neural Architecture Search-based Continuous Authentication Using Auto Augmentation Search

Mobile devices have been playing significant roles in our daily lives, which has made device security and privacy protection extremely important. These mobile devices storing user sensitive and private information, therefore, need rigorous user authentication mechanisms. In this article, we present SearchAuth, a novel continuous authentication system on smartphones exploiting a neural architecture search (NAS) to find an optimal network architecture and an auto augmentation search (AAS) to more effectively train the optimal network along with the best data augmentation policies, by leveraging the accelerometer, gyroscope, and magnetometer on smartphones to capture users’ behavioral patterns. Specifically, SearchAuth consists of three stages, i.e., the offline stage, registration stage, and authentication stage. In the offline stage, we utilize the NAS on sensor data of the accelerometer, gyroscope, and magnetometer to find an optimal network architecture based on the designed search space. With the optimal network architecture, namely, NAS-based model, the AAS automatically optimizes the augmentation of the input data for more effectively training the model that is for feature extraction. In the registration stage, we use the trained NAS-based model to learn and extract deep features from the legitimate user’s data, and train the LOF classifier with 55 features selected by the PCA. In the authentication stage, with the well-trained NAS-based model and LOF classifier, SearchAuth identifies the current user as a legitimate user or an impostor when the user starts operating a smartphone. Based on our dataset, we evaluate the performance of the proposed SearchAuth, and the experimental results demonstrate that SearchAuth surpasses the representative authentication schemes by achieving the best accuracy of 93.95%, F1-score of 94.30%, and EER of 5.30% on the LOF classifier with dataset size of 100.

Deep features fusion for user authentication based on human activity

AbstractThe exponential growth in the use of smartphones means that users must constantly be concerned about the security and privacy of mobile data because the loss of a mobile device could compromise personal information. To address this issue, continuous authentication systems have been proposed, in which users are monitored transparently after initial access to the smartphone. In this study, the authors address the problem of user authentication by considering human activities as behavioural biometric information. The authors convert the behavioural biometric data (considered as time series) into a 2D colour image. This transformation process keeps all the characteristics of the behavioural signal. Time series does not receive any filtering operation with this transformation, and the method is reversible. This signal‐to‐image transformation allows us to use the 2D convolutional networks to build efficient deep feature vectors. This allows them to compare these feature vectors to the reference template vectors to compute the performance metric. The authors evaluate the performance of the authentication system in terms of Equal Error Rate on a benchmark University of Californy, Irvine Human Activity Recognition dataset, and they show the efficiency of the approach.

Touch events and human activities for continuous authentication via smartphone

The security of modern smartphones is related to the combination of Continuous Authentication approaches, Touch events, and Human Activities. The approaches of Continuous Authentication, Touch Events, and Human Activities are silent to the user but are a great source of data for Machine Learning Algorithms. This work aims to develop a method for continuous authentication while the user is sitting and scrolling documents on the smartphone. Touch Events and Smartphone Sensor Features (from the well-known H-MOG Dataset) were used with the addition, for each sensor, of the feature called Signal Vector Magnitude. Several Machine Learning Models have been considered with different experiment setups, 1-class, and 2-class, for evaluation. The results show that the 1-class SVM achieves an accuracy of 98.9% and an F1-score of 99.4%, considering the selected features and the feature Signal Vector Magnitude very significant.

Continuous authentication with feature-level fusion of touch gestures and keystroke dynamics to solve security and usability issues

Behavioral Biometrics (BB) Continuous Authentication (CA) systems monitor user behavior and continuously re-authenticate user identity alongside the initial login process. Most studies use single behavioral modality systems to authenticate users. However, the behaviors of genuine users may change, and systems fail when significant changes occur. This results in either usability or security issues. In the literature, the fusion of biometrics is used to solve this problem and achieves improved results. This paper presents our research on the design and evaluation of new approaches to CA using fusion of touch gestures and keystroke dynamics. To collect the biometric data from mobile device users we have developed the BioGames App which follows an innovative approach based on the gamification paradigm. We examine each modality separately and investigate if we can improve the performance results with a feature-level fusion. For this reason, a new appropriate feature set is developed that combines touch gestures and keystroke dynamics. We used the Multi-Layer Perceptron (MLP) and Long Short-Term Memory (LSTM) and compared their performance. We have shown that feature-level fusion of touch gestures and keystroke dynamics improves the performance of systems and solves security and usability issues. We found that the MLP is superior to LSTM in this context. The MLP achieved Accuracy 98.3% (increased 21.1%), EER 1% (error reduction by 23.7%), TAR 99.4% (increased 46%), TRR 97.4% (increased 10%), FAR 2.6% (reduced by 10.5%), and FRR 0.6% (reduced by 46%).

Revisiting Zero-Trust Security for Internet of Things

The proliferation of Internet of Things (IoT) devices has revolutionized various industries, yet concurrently introduced unprecedented security challenges. Zero-Trust security emerges as a promising paradigm to mitigate the escalating risks associated with IoT ecosystems. This mini review provides a comprehensive analysis of Zero-Trust principles and their application within IoT environments. Beginning with an elucidation of the Zero-Trust framework's foundational tenets, this paper explores its relevance in the context of IoT, emphasizing the necessity for continuous authentication, strict access controls, micro-segmentation, and encryption strategies. Furthermore, it delves into the evolving threat landscape faced by IoT systems and evaluates how Zero-Trust principles effectively counteract these threats, safeguarding sensitive data, ensuring device integrity, and bolstering overall system resilience. Additionally, the review highlights notable challenges and implementation considerations in integrating Zero-Trust security within diverse IoT infrastructures.

On the Long-Term Effects of Continuous Keystroke Authentication

One of the main challenges in deploying a keystroke dynamics-based continuous authentication scheme on smartphones is ensuring low error rates over time. Unstable false rejection rates (FRRs) would lead to frequent phone locks during long-term use, and deteriorating attack detection rates would jeopardize its security benefits. The fact that it is undesirable to train complex deep learning models directly on smartphones or send private sensor data to servers for training present unique deployment constraints, requiring on-device solutions that can be trained fully on smartphones. To improve authentication accuracy while satisfying such real-world deployment constraints, we propose two novel feature engineering techniques: (1) computation of pair-wise correlations between accelerometer and gyroscope sensor values, and (2) on-device feature extraction technique to compute dynamic time warping (DTW) distance measurements between autoencoder inputs and outputs via transfer-learning. Using those two feature sets in an ensemble blender, we achieved 6.4 percent equal error rate (EER) in a public dataset. In comparison, blending two state-of-the-art solutions achieved 14.1 percent EER in the same test settings. Our real-world dataset evaluation showed increasing FRRs (user frustration) over two months; however, through periodic model retraining, we were able to maintain average FRRs around 2.5 percent while keeping attack detection rates around 89 percent. The proposed solution has been deployed in the latest Samsung Galaxy smartphone series to protect secure workspace through continuous authentication.

Ensemble Siamese Network (ESN) Using ECG Signals for Human Authentication in Smart Healthcare System.

Advancements in digital communications that permit remote patient visits and condition monitoring can be attributed to a revolution in digital healthcare systems. Continuous authentication based on contextual information offers a number of advantages over traditional authentication, including the ability to estimate the likelihood that the users are who they claim to be on an ongoing basis over the course of an entire session, making it a much more effective security measure for proactively regulating authorized access to sensitive data. Current authentication models that rely on machine learning have their shortcomings, such as the difficulty in enrolling new users to the system or model training sensitivity to imbalanced datasets. To address these issues, we propose using ECG signals, which are easily accessible in digital healthcare systems, for authentication through an Ensemble Siamese Network (ESN) that can handle small changes in ECG signals. Adding preprocessing for feature extraction to this model can result in superior results. We trained this model on ECG-ID and PTB benchmark datasets, achieving 93.6% and 96.8% accuracy and 1.76% and 1.69% equal error rates, respectively. The combination of data availability, simplicity, and robustness makes it an ideal choice for smart healthcare and telehealth.

Continuous User Authentication on Multiple Smart Devices

Recent developments in the mobile and intelligence industry have led to an explosion in the use of multiple smart devices such as smartphones, tablets, smart bracelets, etc. To achieve lasting security after initial authentication, many studies have been conducted to apply user authentication through behavioral biometrics. However, few of them consider continuous user authentication on multiple smart devices. In this paper, we investigate user authentication from a new perspective—continuous authentication on multi-devices, that is, continuously authenticating users after both initial access to one device and transfer to other devices. In contrast to previous studies, we propose a continuous user authentication method that exploits behavioral biometric identification on multiple smart devices. In this study, we consider the sensor data captured by accelerometer and gyroscope sensors on both smartphones and tablets. Furthermore, multi-device behavioral biometric data are utilized as the input of our optimized neural network model, which combines a convolutional neural network (CNN) and a long short-term memory (LSTM) network. In particular, we construct two-dimensional domain images to characterize the underlying features of sensor signals between different devices and then input them into our network for classification. In order to strengthen the effectiveness and efficiency of authentication on multiple devices, we introduce an adaptive confidence-based strategy by taking historical user authentication results into account. This paper evaluates the performance of our multi-device continuous user authentication mechanism under different scenarios, and extensive empirical results demonstrate its feasibility and efficiency. Using the mechanism, we achieved mean accuracies of 99.8% and 99.2% for smartphones and tablets, respectively, in approximately 2.3 s, which shows that it authenticates users accurately and quickly.

BLUFADER: Blurred face detection & recognition for privacy-friendly continuous authentication

Authentication and de-authentication phases should occur at the beginning and end of secure user sessions, respectively. A secure session requires the user to pass the former, but the latter is often underestimated or ignored. Unattended or dangling sessions expose users to well-known Lunchtime Attacks. To mitigate this threat, researchers focused on automated de-authentication systems, either as a stand-alone mechanism or as a result of continuous authentication failures. Unfortunately, no single approach offers security, privacy, and usability. Face-recognition methods, for example, may be suitable for security and usability, but they violate user privacy by continuously recording their actions and surroundings.In this work, we propose BLUFADER, a novel continuous authentication system that takes advantage of blurred face detection and recognition to fast, secure, and transparent de-authenticate users, preserving their privacy. We obfuscate a webcam with a physical blur layer and use deep learning algorithms to perform face detection and recognition continuously. To evaluate BLUFADER’s practicality, we collected two datasets formed by 30 recruited subjects (users) and thousands of physically blurred celebrity photos. The de-authentication system was trained and evaluated using the former, while the latter was used to appraise the privacy and increase variance at training time. To guarantee the privacy-preserving effectiveness of the selected physical blurring filter, we show that state-of-the-art deblurring models are not able to revert our physical blur. Further, we demonstrate that our approach outperforms state-of-the-art methods in detecting blurred faces, achieving up to 95% accuracy. Moreover, BLUFADER effectively de-authenticates users up to 100% accuracy in under 3 seconds, while satisfying security, privacy, and usability requirements. Last, our continuous authentication face recognition module based on Siamese Neural Network preventively protect users from adversarial attacks, enhancing the overall system security.

Privacy-Preserving Continuous Authentication for Mobile and IoT Systems Using Warmup-Based Federated Learning

Continuous authentication for mobile devices acknowledges users by studying their behavioural interactions with their devices. It provides an extended protection mechanism that supplies an additional layer of security for smartphones and Internet of Things (IoT) devices and locks out intruders in cases of stolen credentials or hijacked sessions. Most of the continuous authentication efforts in the literature consist of collecting behavioural, sensory data from users and extracting statistical patterns through adopting various Machine Learning (ML) techniques. The main drawback of these approaches is their heavy reliance on acquiring the users' personal data, which exposes the latter's privacy. To address this limitation, we introduce a novel Federated Learning (FL) based continuous authentication mechanism for mobile and IoT devices. Our approach preserves the users' privacy by allowing each individual to locally train an ML model that captures his/her behaviour and then shares the model weights with the server for global aggregation. An extended scheme with a warmup FL approach for continuous authentication is proposed. Performance evaluation is done with a unique non-IID dataset built from three well-known datasets MNIST, CIFAR-10 and FEMNIST. The extensive experimental results show a major accuracy increase in user authentication.

Zero trust architecture in IAM with AI integration

ZTA is a new model of enterprise cybersecurity that stands for continuous authentication, strict access control and dynamic verification for data, assets and identities of enterprises in multilayered infrastructures. ZTA ensures that each and every incoming request to access people, devices or applications is constantly compared to the organisation’s policy and approved, no matter if it is coming inside or outside a network, unlike a traditional perimeter-based security strategy. In an effort to enhance the compliance standards and lower the attack surface, this article expands on the basic tenets of ZTA, such as adding IAM to regulate access based on the role and permission systems. ZTA is further enhanced by AI that enables the real-time identification of threats, dynamic security access control, and risk estimation. By adopting the AI approach, ZTA can make intelligent decisions, and this makes companies able to counteract the ever-incoming cyber threats. Among the areas where ZTA and AI applications are being adopted are cloud environments, remote workforces, IoT devices, and microservices. Further research prospects are also enumerated in this document, such as developing AI-based behavioural analytics, safeguarding Edge and IoT applications, incorporating improved threat intelligence, and incorporating machine learning in ZTA processes. These developments will keep ZTA as a strong and adaptive cybersecurity framework for any corporate infrastructures and protect them from threats in related modern digital landscapes.

A Robust Continuous Authentication System Using Smartphone Sensors and Wasserstein Generative Adversarial Networks

Since the continuous authentication (CA) system based on smartphone sensors has been facing the challenge of the low-data regime under some practical scenarios, which leads to low accuracy of CA, it needs to be solved urgently. To this end, currently, the generative adversarial networks (GAN) provide a powerful method to train the result generative model that could generate very convincing verisimilar data. The framework of the GAN and its variants shed much light on improving the performance of CA. Therefore, in this article, we propose a continuous authentication system on smartphones based on a Wasserstein generative adversarial network (WGAN) for sensor data augmentation, which utilizes accelerometers, gyroscopes, and magnetometers of smartphone sensors to sense phone movements caused by user operation behavior. Specifically, based on sensor data under different user activities, the WGAN is used to create additional data in training data for data augmentation. With the augmented data, we design a convolutional neural network to learn and extract deep features from sensor data, and then use four classifiers of RF, OCSVM, DT, and KNN to train these features. Finally, we train and test on the HMOG dataset, and the results show that the EER of the authentication system is between 3.68% and 6.39% on the sensor data with a time window of 2 s.

NF-Heart

The increasingly remote workforce resulting from the global coronavirus pandemic has caused unprecedented cybersecurity concerns to organizations. Considerable evidence has shown that one-pass authentication fails to meet security needs when the workforce work from home. The recent advent of continuous authentication (CA) has shown the potential to solve this predicament. In this paper, we propose NF-Heart, a physiological-based CA system utilizing a ballistocardiogram (BCG). The key insight is that the BCG measures the body's micro-movements produced by the recoil force of the body in reaction to the cardiac ejection of blood, and we can infer cardiac biometrics from BCG signals. To measure BCG, we deploy a lightweight accelerometer on an office chair, turning the common chair into a smart continuous identity "scanner". We design multiple stages of signal processing to decompose and transform the distorted BCG signals so that the effects of motion artifacts and dynamic variations are eliminated. User-specific fiducial features are then extracted from the processed BCG signals for authentication. We conduct comprehensive experiments on 105 subjects in terms of verification accuracy, security, robustness, and long-term availability. The results demonstrate that NF-Heart achieves a mean balanced accuracy of 96.45% and a median equal error rate of 3.83% for CA. The proposed signal processing pipeline is effective in addressing various practical disturbances.

Multisensor-Based Continuous Authentication of Smartphone Users With Two-Stage Feature Extraction

The one-time authentication mechanism in traditional authentication methods cannot continuously authenticate smartphone users’ identities throughout the session. Continuous authentication based on the behavioral biometrics recorded by the built-in sensors can solve this issue. However, the existing methods based on multisensor have poor ability to extract valuable features that can represent smartphone users’ behavioral patterns. This article proposes a novel method combining the manual construction and the deep metric learning method to perform two-stage feature extraction, respectively. We transform the time-series raw data from three sensors (accelerometer, gyroscope, and magnetometer) into 69 statistical features in the first stage. Furthermore, unlike the existing serial feature fusion methods, we innovatively fuse the constructed statistical features from three sensors into a three-channel matrix. Then, the fused features matrix with a three-channel is fed to the deep metric learning model for the second stage of feature extraction. We use the elliptic envelope algorithm to classify the user as a legitimate user or an impostor. Finally, we evaluate the performance of the proposed method on two public data sets. Experimental results show that our method can achieve an average accuracy of 99.71% and an average equal error rate (EER) of 0.56% on the hand movement, movement, orientation, and grasp data set, and an average accuracy of 99.59% and an average EER of 0.61% on the BrainRun data set.

Heart ID: Biometric Identification Using Wearable MIMO RF Heart Sensors

Biometric identification (ID) has become increasingly prevalent in the digital era. Static biometric methods, such as fingerprint and facial recognition are widely accepted, yet generally vulnerable to targeted presentation attacks. Current development has expanded to dynamic biometrics, such as gait and electrocardiogram, that enable continuous authentication and are significantly more resistant to presentation attacks. However, dynamic biometrics often involve cumbersome acquisition which restricts their widespread use. Here, we introduce Heart ID, a novel dynamic biometric system that uses near-field coherent sensing (NCS) with a multiple-in multiple-out (MIMO) radio-frequency (RF) antenna setup to non-invasively acquire detailed recordings of internal cardiac dielectric boundary motion over clothing. NCS couples localized energy to the heart to derive interpersonal structural differences, while MIMO significantly increases the biometric entropy compared to single-point observation. We performed a human study of 20 subjects as well as 2 longitudinal evaluations, and employed an unsupervised feature extraction method to explore the ID performance of this new biometric. We found an ensemble classification approach using features derived from unsupervised learning can achieve accuracy exceeding 99% at a 40-second epoch.