Continuous User Authentication Research Articles

FacekeyID: an adaptive weighted sum score-based fusion framework for continuous user authentication

FacekeyID: an adaptive weighted sum score-based fusion framework for continuous user authentication

Using Behavioural Biometrics and Machine Learning in Smart Gadgets for Continuous User Authentication Purposes

In the ever-evolving realm of technology, the identification of human activities using intelligent devices such as smartwatches, fitness bands, and smartphones has emerged as a crucial area of study. These devices, equipped with inertial sensors, gather a wealth of data and provide insights into users' movements and behaviors. These data not only serve practical purposes, but also hold significant implications for domains such as healthcare and fitness tracking. Traditionally, these devices have been employed to monitor various health metrics such as step counts, calorie expenditure, and real-time blood pressure monitoring. However, recent research has shifted its focus to leveraging the data collected by these sensors for user authentication purposes. This innovative approach involves the utilization of Machine Learning (ML) models to analyze the routine data captured by sensors in smart devices employing ML algorithms, which can recognize and authenticate users based on their unique movement patterns and behaviors. This introduces a paradigm shift from traditional one-time authentication methods to continuous authentication, adding an extra layer of security to protect users against potential threats. Continuous authentication offers several advantages over its conventional counterparts. First, it enhances security by constantly verifying a user's identity through their interaction with the device, thereby mitigating the risk of unauthorized access. Second, it provides a seamless and nonintrusive user experience, eliminating the need for repetitive authentication prompts. Moreover, it offers robust protection against various threats such as identity theft, unauthorized access, and device tampering. The application of continuous authentication extends beyond individual devices and encompasses interconnected systems and networks. This holistic approach ensures a comprehensive security across digital platforms and services. The experiments demonstrate that the logistic regression model achieves an accuracy of 82.32% on the test dataset, highlighting its robustness for binary classification tasks. Additionally, the random forest model outperforms with a 92.18% accuracy, emphasizing its superior capability in handling complex feature interactions. In the study, the sequential neural network achieved an accuracy of 92% on the HAR dataset, outperforming traditional machine learning models by a significant margin. The model also demonstrated robust generalization capabilities with a minimal drop in performance across various cross-validation folds.

Explaining vulnerabilities of heart rate biometric models securing IoT wearables

In the field of health informatics, extensive research has been conducted to predict diseases and extract valuable insights from patient data. However, a significant gap exists in addressing privacy concerns associated with data collection. Therefore, there is an urgent need to develop a machine-learning authentication model to secure the patients’ data seamlessly and continuously, as well as to find potential explanations when the model may fail. To address this challenge, we propose a unique approach to secure patients’ data using novel eigenheart features calculated from coarse-grained heart rate data. Various statistical and visualization techniques are utilized to explain the potential vulnerabilities of the model. Though it is feasible to develop continuous user authentication models from readily available heart rate data with reasonable performance, they are affected by factors such as age and Body Mass Index (BMI). These factors will be crucial for developing a more robust authentication model in the future.

Personalized user authentication system using wireless EEG headset and machine learning

In the realm of authentication, biometric verification has gained widespread adoption, especially within high-security user authentication systems. Although convenient, existing biometric systems are susceptible to a number of security vulnerabilities, including spoofing tools such as gummy fingers for fingerprint systems and voice coders for voice recognition systems. In this regard, brainwave-based authentication has emerged as a novel form of biometric scheme that has the potential to overcome the security limitations of existing systems while facilitating additional capabilities, such as continuous user authentication. In this study, we focus on a data-driven approach to Electroencephalography (EEG)-based authentication, guided by the power of machine learning algorithms. Our methodology addresses the fundamental challenge of distinguishing real users from intruders by training classification algorithms to the unique EEG signatures of every individual. The system is characterized by its convenience, ensuring real-time applicability without compromising its efficiency. By employing a commercially available single-channel EEG sensor and extracting a set of 8 power spectral features (delta [0–4 Hz], theta [4–8 Hz], low alpha [8–10 Hz], high alpha [10–12 Hz], low beta [12–20 Hz], high beta [20–30 Hz], low gamma [30–60 Hz], high gamma [60–100 Hz]), a commendable mean accuracy of 85.4% was achieved.

From Clicks to Security: Investigating Continuous Authentication via Mouse Dynamics

In the realm of computer security, the importance of efficient and reliable user authentication methods has become increasingly critical. This paper examines the potential of mouse movement dynamics as a consistent metric for continuous authentication. By analysing user mouse movement patterns in two contrasting gaming scenarios, "Team Fortress" and "Poly Bridge," we investigate the distinctive behavioral patterns inherent in high-intensity and low-intensity UI interactions. The study extends beyond conventional methodologies by employing a range of machine learning models. These models are carefully selected to assess their effectiveness in capturing and interpreting the subtleties of user behavior as reflected in their mouse movements. This multifaceted approach allows for a more nuanced and comprehensive understanding of user interaction patterns. Our findings reveal that mouse movement dynamics can serve as a reliable indicator for continuous user authentication. The diverse machine learning models employed in this study demonstrate competent performance in user verification, marking an improvement over previous methods used in this field. This research contributes to the ongoing efforts to enhance computer security and highlights the potential of leveraging user behavior, specifically mouse dynamics, in developing robust authentication systems.

Data-Augmentation-Enabled Continuous User Authentication via Passive Vibration Response

Continuous identity authentication is critical for privacy protection throughout an entire user login session. In this paper, we propose a continuous user authentication mechanism namely, which employs the vibration responses from hand biometrics and is passively activated by natural user-device interaction. Hand vibration responses are embedded in the mechanical vibration of a force-bearing body consisting of one mobile device and one user hand. A built-in accelerometer of the device can capture hand-dependent vibration signals. Considering the concealment of vibration generation and the non-replicability of hand structure, it’s difficult for attackers to counterfeit user identity. Moreover, for ensuring the robustness of authentication performance to tapping behavior interference, we construct a data augmentation module jointly leveraging a signal processing and learning-based pipeline. It can generate enough vibration responses representing hand structure biometrics under various behaviors, thereby making comprehensively understand vibration response variation. We prototype on smartphones, and extensive experiments demonstrate that can achieve satisfactory authentication accuracy.

Cross-Modality Continuous User Authentication and Device Pairing With Respiratory Patterns

Cross-Modality Continuous User Authentication and Device Pairing With Respiratory Patterns

Passive User Authentication Utilizing Two-Dimensional Features for IIoT Systems

Passive user authentication is critical for the secure operation of Industrial Internet of Things (IIoT) systems. By jointly utilizing both the time-varying characteristics of the user sequential operation actions and spatial variation characteristics of channel state information (CSI) caused by these actions, this paper proposes a novel two-dimensional passive authentication framework for IIoT systems. In particular, we construct the time-varying operation action sequences from the routine work process of a user and apply the Hidden Markov Model to characterize behavioral biometric characteristics of the user, and also employ the eXtreme Gradient Boosting model to depict the spatial variation characteristics of CSI related to the user. By designing two classifiers corresponding these two characteristics and assigning each classifier an appropriate weight, we propose a two-dimensional user authentication framework for continuous and non-intrusive user authentication in IIoT scenarios. Extensive experiments are conducted to illustrate the authentication performance of the proposed authentication framework in terms of false acceptance rate, false rejection rate and equal-error rate. We further investigate the related authentication efficiency issues like the sensitivity to the weights for classifiers, the sensitivity to authentication time and the capability of resisting against impersonation attacks.

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.

A Survey on Quantitative Risk Estimation Approaches for Secure and Usable User Authentication on Smartphones.

Mobile user authentication acts as the first line of defense, establishing confidence in the claimed identity of a mobile user, which it typically does as a precondition to allowing access to resources in a mobile device. NIST states that password schemes and/or biometrics comprise the most conventional user authentication mechanisms for mobile devices. Nevertheless, recent studies point out that nowadays password-based user authentication is imposing several limitations in terms of security and usability; thus, it is no longer considered secure and convenient for the mobile users. These limitations stress the need for the development and implementation of more secure and usable user authentication methods. Alternatively, biometric-based user authentication has gained attention as a promising solution for enhancing mobile security without sacrificing usability. This category encompasses methods that utilize human physical traits (physiological biometrics) or unconscious behaviors (behavioral biometrics). In particular, risk-based continuous user authentication, relying on behavioral biometrics, appears to have the potential to increase the reliability of authentication without sacrificing usability. In this context, we firstly present fundamentals on risk-based continuous user authentication, relying on behavioral biometrics on mobile devices. Additionally, we present an extensive overview of existing quantitative risk estimation approaches (QREA) found in the literature. We do so not only for risk-based user authentication on mobile devices, but also for other security applications such as user authentication in web/cloud services, intrusion detection systems, etc., that could be possibly adopted in risk-based continuous user authentication solutions for smartphones. The target of this study is to provide a foundation for organizing research efforts toward the design and development of proper quantitative risk estimation approaches for the development of risk-based continuous user authentication solutions for smartphones. The reviewed quantitative risk estimation approaches have been divided into the following five main categories: (i) probabilistic approaches, (ii) machine learning-based approaches, (iii) fuzzy logic models, (iv) non-graph-based models, and (v) Monte Carlo simulation models. Our main findings are summarized in the table in the end of the manuscript.

An omnidirectional approach to touch-based continuous authentication

This paper focuses on how touch interactions on smartphones can provide a continuous user authentication service through behaviour captured by a touchscreen. While efforts are made to advance touch-based behavioural authentication, researchers often focus on gathering data, tuning classifiers, and enhancing performance by evaluating touch interactions in a sequence rather than independently. However, such systems only work by providing data representing distinct behavioural traits. The typical approach separates behaviour into touch directions and creates multiple user profiles. This work presents an omnidirectional approach which outperforms the traditional method independent of the touch direction - depending on optimal behavioural features and a balanced training set. Thus, we evaluate five behavioural feature sets using the conventional approach against our direction-agnostic method while testing several classifiers, including an Extra-Tree and Gradient Boosting Classifier, which is often overlooked. Results show that in comparison with the traditional, an Extra-Trees classifier and the proposed approach are superior when combining strokes. However, the performance depends on the applied feature set. We find that the TouchAlytics feature set outperforms others when using our approach when combining three or more strokes. Finally, we highlight the importance of reporting the mean area under the curve and equal error rate for single-stroke performance and varying the sequence of strokes separately.

Continuous Mobile User Authentication Using a Hybrid CNN-Bi-LSTM Approach

Internet of Things (IoT) devices incorporate a large amount of data in several fields, including those of medicine, business, and engineering. User authentication is paramount in the IoT era to assure connected devices’ security. However, traditional authentication methods and conventional biometrics-based authentication approaches such as face recognition, fingerprints, and password are vulnerable to various attacks, including smudge attacks, heat attacks, and shoulder surfing attacks. Behavioral biometrics is introduced by the powerful sensing capabilities of IoT devices such as smart wearables and smartphones, enabling continuous authentication. Artificial Intelligence (AI)-based approaches introduce a bright future in refining large amounts of homogeneous biometric data to provide innovative user authentication solutions. This paper presents a new continuous passive authentication approach capable of learning the signatures of IoT users utilizing smartphone sensors such as a gyroscope, magnetometer, and accelerometer to recognize users by their physical activities. This approach integrates the convolutional neural network (CNN) and recurrent neural network (RNN) models to learn signatures of human activities from different users. A series of experiments are conducted using the MotionSense dataset to validate the effectiveness of the proposed method. Our technique offers a competitive verification accuracy equal to 98.4%. We compared the proposed method with several conventional machine learning and CNN models and found that our proposed model achieves higher identification accuracy than the recently developed verification systems. The high accuracy achieved by the proposed method proves its effectiveness in recognizing IoT users passively through their physical activity patterns.

Reduction of Computational Amount in Person Verification Based on SVM Using Evoked Brain Wave by Ultrasound

For realizing continuous authentication of users, we have studied to use an electroencephalogram (EEG) evoked by ultrasound as biometrics. Users are presented only the ultrasound of their memorable music and verified whether genuine or not using the induced components of EEG. In our previous studies, the verification error rate of 0 % was achieved using multiple quantities in EEG as individual features and a support vector machine (SVM) as a verification method; however, it required a large amount of computation for processing SVM models. Thus, we reduce the number of SVM models by applying two selection methods of features and electrodes, which have been previously introduced. Furthermore, we examine the usage rates of features and electrodes in the reduced SVM models. By using only the electrodes with high usage rates, the verification error rate of 0 % is guaranteed with a small amount of computation.

Implicit Continuous User Authentication for Mobile Devices based on Deep Reinforcement Learning

The predominant method for smart phone accessing is confined to methods directing the authentication by means of Point-of-Entry that heavily depend on physiological biometrics like, fingerprint or face. Implicit continuous authentication initiating to be loftier to conventional authentication mechanisms by continuously confirming users’ identities on continuing basis and mark the instant at which an illegitimate hacker grasps dominance of the session. However, divergent issues remain unaddressed. This research aims to investigate the power of Deep Reinforcement Learning technique to implicit continuous authentication for mobile devices using a method called, Gaussian Weighted Cauchy Kriging-based Continuous Czekanowski’s (GWCK-CC). First, a Gaussian Weighted Non-local Mean Filter Preprocessing model is applied for reducing the noise present in the raw input face images. Cauchy Kriging Regression function is employed to reduce the dimensionality. Finally, Continuous Czekanowski’s Classification is utilized for proficient classification between the genuine user and attacker. By this way, the proposed GWCK-CC method achieves accurate authentication with minimum error rate and time. Experimental assessment of the proposed GWCK-CC method and existing methods are carried out with different factors by using UMDAA-02 Face Dataset. The results confirm that the proposed GWCK-CC method enhances authentication accuracy, by 9%, reduces the authentication time, and error rate by 44%, and 43% as compared to the existing methods.

MAUTH: Continuous User Authentication Based on Subtle Intrinsic Muscular Tremors

Continuous authentication is viewed to be increasingly important for mobile devices, which store a wide range of private data and sensitive information of users. Traditional continuous authentication methods need user inputs (e.g. typing, sliding). In this work, we present MAUTH, a zero-effect continuous authentication scheme for mobile devices. With the built-in motion sensors on commercial off-the-shelf (COTS) devices, MAUTH can continuously extract, classify and verify the unique tremor features of users on how their body intrinsically shakes during the normal use of such devices. As a result, it is extremely difficult if not impossible to reproduce the same set of tremors as individuals differ in their muscle development. We implement MAUTH as a software on Android-based smartphones, which demonstrates that MAUTH is light-weight and unobtrusive to its users. We conduct extensive real-world experiments and trace-driven simulations in controlled and uncontrolled environments on 21 volunteers. The results show that MAUTH is difficult to counterfeit and achieves a low average false positive rate (FPR) of 6.73% under real-world spoofing attacks. Moreover, MAUTH is comfortable to use and can achieve a low average false negative rate (FNR) of 2.2% during uncontrolled and continuous usage of devices, leveraging isolation-forest-based classifiers trained with only 40 training samples.

Sensor-based continuous user authentication on smartphone through machine learning

With the rapid development of hardware and software technology, many end-users have often stored their data on smartphones through several in-built sensors. Thus, the security of stored data on smartphones has become a significant concern. This has fueled the importance of entry-point authentication methods on smartphones. Many entry-point authentication methods have failed to offer security due to insider or side-channel attacks. This article introduces a sensor-based continuous user authentication approach on the smartphone through multi-modal behavioral biometrics and a machine learning model to tackle the aforementioned issues. The proposed approach captures the touch and motion-based behavioral biometrics through the touchscreen and inertial sensors of the device. Then, the proposed approach extracts several features from captured behavioral data and selects the best set of features through a filter-based feature selection technique. Further, we implement a nonlinear support vector machine with optimized hyperparameters for training and predicting the features to generate the scores. We apply score-level fusion on generated scores of several sensors to compute the final score for identification of the genuine user. In this article, we systematically evaluate the proposed approach with the most commonly used behavioral activities of the smartphone user in our daily life. The experiment results on all behavioral activities show that the proposed approach obtained the best authentication score compared to the other machine learning models, and state-of-the-art methods. Finally, we conclude our article by addressing the limitations of the proposed approach and practical research issues for future exploration.

Retraction Note: Continuous user authentication based score level fusion with hybrid optimization

Retraction Note: Continuous user authentication based score level fusion with hybrid optimization

A Personalized User Authentication System Based on EEG Signals.

Conventional biometrics have been employed in high-security user-authentication systems for over 20 years now. However, some of these modalities face low-security issues in common practice. Brainwave-based user authentication has emerged as a promising alternative method, as it overcomes some of these drawbacks and allows for continuous user authentication. In the present study, we address the problem of individual user variability, by proposing a data-driven Electroencephalography (EEG)-based authentication method. We introduce machine learning techniques, in order to reveal the optimal classification algorithm that best fits the data of each individual user, in a fast and efficient manner. A set of 15 power spectral features (delta, theta, lower alpha, higher alpha, and alpha) is extracted from three EEG channels. The results show that our approach can reliably grant or deny access to the user (mean accuracy of 95.6%), while at the same time poses a viable option for real-time applications, as the total time of the training procedure was kept under one minute.

Evaluating multi-modal mobile behavioral biometrics using public datasets

Behavioral biometric-based continuous user authentication is promising for securing mobile phones while complementing traditional security mechanisms. However, the existing state of art perform continuous authentication to evaluate deep learning models, but lacks examining different feature sets over the data. Therefore, we evaluate the performance of user authentication based on acceleration, gyroscope (angular velocity), and swipe data from two public mobile datasets, HMOG (Hand-Movement, Orientation, and Grasp) (Sitová et al., (2015) dataset et al. (2015)) and BB-MAS (Behavioral Biometrics Multi-device and multi-Activity data from Same users) (Belman et al., (2019) dataset et al. (2019)) extracted with different feature sets to observe the variation in authentication performance. We evaluate the performances of both individual modalities and their fusion. Since the swipe data is intermittent but the motion event data continuous, we evaluate fusion of swipes with motion events that occur within the swipes versus fusion of motion events outside of swipes. Moreover, we extract Frank et al.’s (2012) Touchalytics features Frank et al. (2012) on the swipe data but three different feature sets (median, HMOG (Sitová et al. (2015)), and Shen’s (Shen et al. (2017))) on the motion event data, among which the Shen’s features were shown to perform the best. More specifically, we perform score-level fusion for a single modality utilizing binary SVMs (Support Vector Machine). Furthermore, we evaluate the fusion of multiple modalities using Nandakumar’s likelihood ratio-based score fusion (Nandakumar et al. (2007)) by utilizing both one-class and binary SVMs. The best EERs (Equal Error Rates) of fusing all three modalities when using the one-class SVMs are 8.8% and 0.9% for HMOG and BB-MAS respectively. On the other hand, the best EERs in the case of binary SVMs are 1.5% and 0.2% respectively. Observing the better performances of BB-MAS compared to HMOG in swipe-based experiments, we examine the difference of swipe trajectory between the two datasets and find that BB-MAS has longer swipes than HMOG which would explain the performance difference in the experiments.

A method of detecting information security incidents based on anomalies in the user's biometric behavioral characteristics

Nowadays a significant amount of attacks on information systems are multi-stage attacks. In many cases the key subjects of attacks are insiders. The actions of an insider differ from the activity of a legitimate user, so it is possible for the latter to form a model of his behavior. Then the differences from the specified model can be classified as information security events or incidents. Existing approaches to anomaly detection in user activity use separate characteristics of user behavior, without taking into account their interdependencies and dependencies on various factors. The task of the study is to form a comprehensive characteristic of the user`s behavior when using a computer — a “digital pattern” for detecting information security events and incidents. The essence of the method is in the formation of a digital pattern of the user’s activity by analyzing his behavioral characteristics and their dependencies selected as predictors. The developed method involves the formation of a model through unsupervised machine learning. The following algorithms were considered: one-class support vector machine, isolating forest and elliptic envelope. The Matthews correlation coefficient was chosen as the main metric for the quality of the models, but other indicators were also taken into consideration. According to the selected quality metrics, a comparative analysis of algorithms with different parameters was conducted. An experiment was carried out to evaluate the developed method and compare its effectiveness with the closest analogue. Real data on the behavior of 138 users was used to train and evaluate models within the studied methods. According to the results of the comparative analysis, the proposed method showed great performance for all the considered metrics, including an increase in the Matthews correlation coefficient by 0.6125 compared to the anomaly detection method by keystroke dynamics. The proposed method can be used for continuous user authentication from unauthorized access and identifying information security incidents related to the actions of insiders.