Continuous Authentication Research Articles

Behavioral Biometrics-based Continuous Authentication Using A Lightweight Latent Representation Masked One-Class Autoencoder

Behavioral Biometrics-based Continuous Authentication Using A Lightweight Latent Representation Masked One-Class Autoencoder

A Comprehensive Review on Secure Biometric-Based Continuous Authentication and User Profiling

A Comprehensive Review on Secure Biometric-Based Continuous Authentication and User Profiling

MBBFAuth: Multimodal Behavioral Biometrics Fusion for Continuous Authentication on Non-Portable Devices

MBBFAuth: Multimodal Behavioral Biometrics Fusion for Continuous Authentication on Non-Portable Devices

Continuous Authentication for Consumer Electronics in Smart City Surveillance

Continuous Authentication for Consumer Electronics in Smart City Surveillance

A Traceable Continuous Authentication Scheme for Avatars in Large-Scale Commercial Activities

A Traceable Continuous Authentication Scheme for Avatars in Large-Scale Commercial Activities

A Secure, Flexible, and PPG-Based Biometric Scheme for Healthy IoT Using Homomorphic Random Forest

Advances in the Internet of Things such as biosensing and camera-capturing technologies have also resulted in biometric-based authentication approaches becoming more viable. Photoplethysmography (PPG), for example, can be leveraged to provide better biometric features for continuous authentication, in comparison to other biometrics such as fingerprint. However, the fewer morphological features in PPG signals can complicate the accurate authentication of PPG signals. Furthermore, one has to also consider transmission security and PPG template storage security. These two considerations are typically not taken into consideration in most existing PPG-based authentication schemes. Therefore, we design a secure PPG-based biometric system to achieve accurate authentication with biometric privacy protection. In our design, Homomorphic Random Forest is adopted to classify the homomorphically encrypted biometric features, thus protecting the user’s PPG biometrics from being compromised in authentication. Furthermore, beat qualification screening is set up to avoid the interference of unqualified signals, and 19 features with the least redundancy from the 541 features extracted are selected as the biometric features of the user. Doing so allows us to ensure the accuracy of authentication, as demonstrated in our evaluations using five PPG databases collected by three different collection methods (contact, remote, and monitor). In addition, our experiments adopt PPG signals acquired from remote cameras, which are not considered in other PPG-based biometric systems. The experimental results show that the average accuracy of our biometric system is 96.4%, the F1 score is 96.1%, the EER is 2.14%, and the authentication time is about 0.5s.

Revolutionizing Healthcare: A Comprehensive Framework for Personalized IoT and Cloud Computing-Driven Healthcare Services with Smart Biometric Identity Management

Medical care conveyance has been transformed by the Internet of Things (IoT's) combination into wellbeing systems, which provides doctors and patients with continuous on-request services. However, this coordination poses questions with respect to the precision of the information and possible security risks. This research expects to present a sharp character the executives structure planned for IoT and distributed computing based personalized medical care frameworks. The purpose is to upgrade confirmation processes while restricting security threats through the double-dealing of multimodal encoded biometric features. The suggested approach incorporates biometric-based continuous authentication together with combined and concentrated personality access strategies. To safeguard patient information in the cloud, it combines electrocardiogram (ECG) and photoplethysmogram (PPG) signals for authentication, which is further bolstered by homomorphic encryption (HE). An AI (ML) model was used to assess the system's reasonability including a dataset of 20 clients in various seating configurations. The merged based biometric structure defeated standalone ECG or PPG signal-based procedures in perceiving and authenticating every client with 100% exactness. The proposed framework makes significant improvements to the privacy and security of personalized healthcare frameworks. It fulfills the essential security necessities and is by the by viable enough to run on low-end processors. It guarantees trustworthy authentication and protects against conventional security threats by utilizing multimodal biometric features and cutting-edge encryption techniques.

ECG Biometric Authentication Using Self-Supervised Learning for IoT Edge Sensors.

Wearable Internet of Things (IoT) devices are gaining ground for continuous physiological data acquisition and health monitoring. These physiological signals can be used for security applications to achieve continuous authentication and user convenience due to passive data acquisition. This paper investigates an electrocardiogram (ECG) based biometric user authentication system using features derived from the Convolutional Neural Network (CNN) and self-supervised contrastive learning. Contrastive learning enables us to use large unlabeled datasets to train the model and establish its generalizability. We propose approaches enabling the CNN encoder to extract appropriate features that distinguish the user from other subjects. When evaluated using the PTB ECG database with 290 subjects, the proposed technique achieved an authentication accuracy of 99.15%. To test its generalizability, we applied the model to two new datasets, the MIT-BIH Arrhythmia Database and the ECG-ID Database, achieving over 98.5% accuracy without any modifications. Furthermore, we show that repeating the authentication step three times can increase accuracy to nearly 100% for both PTBDB and ECGIDDB. This paper also presents model optimizations for embedded device deployment, which makes the system more relevant to real-world scenarios. To deploy our model in IoT edge sensors, we optimized the model complexity by applying quantization and pruning. The optimized model achieves 98.67% accuracy on PTBDB, with 0.48% accuracy loss and 62.6% CPU cycles compared to the unoptimized model. An accuracy-vs-time-complexity tradeoff analysis is performed, and results are presented for different optimization levels.

CT-Auth: Capacitive Touchscreen-Based Continuous Authentication on Smartphones

CT-Auth: Capacitive Touchscreen-Based Continuous Authentication on Smartphones

Integrating Artificial Intelligence, machine learning, and data analytics in cybersecurity: A holistic approach to advanced threat detection and response

Introduction: The integration of artificial intelligence (AI), machine learning (ML), and data analytics is revolutionizing cybersecurity practices. With the advancement in technology and new threats emerging in the cyberspace, conventional approaches to security are not effectively sufficient. This paper aims at identifying how these sophisticated technologies improve the methods of threat identification, response, and the overall analytical capability to strengthen the computerized structures against modern SNEs. The threat is changing at incredible speeds, making it impossible to just wait for new threats to unfold and take a response. AI&ML are capable to analyses enormous quantity of data in extremely short time, as well as find patterns and changing previous unnoticed by analysts, automatically respond to threats in real time. Data analytics forms the bedrock on which the advanced systems are built and serve to process and analyze a large chunk of the security related information. The combination of these technologies provides a strong foundation for the cybersecurity environment that can be responsive to emerging threats, utilize prior attacks for training purposes, and self-develop the methodology for better protection. Methodology: The study employed a comprehensive search strategy across multiple electronic databases, including IEEE Xplore, ACM Digital Library, ScienceDirect, Scopus, and Google Scholar. Keywords related to AI, ML, data analytics, and cybersecurity were used in combination with Boolean operators. To make the outcome more meaningful and relevant, the general criteria for the eligibility of the papers were as follows. The selection process involved two phases: Title and abstract evaluation for the inclusion in the initial set of studies and subsequent full-text review of these studies. Some of our extraction process involved the use of a data extraction form to gather specific details from each of the study included in the analysis. To evaluate the quality of the studies included, the CASP tools were used with slight modifications. In this study, two independent reviewers participated in the decision on the study inclusion, data extraction, and quality assessment to reduce bias. This approach of writing helped in providing a comprehensive and methodical analysis of the contemporary state and potential developments in the context of AI and ML in the realm of cybersecurity. Results and Discussion: The review highlights that AI and ML greatly boost the threat detection by detecting patterns and anomalies within large volumes of security data. These technologies can be used to descend new and previously unknown type of attack known as zero-day attack & APTs (advanced persistent threats). Using AI and ML for predictive analytics enables the organization to leverage previous attacks and contexts to predict future attacks, and prepare for their defense. The use of AI in response to security threats also minimizes response time in times of security threats and optimizes processes. These technologies integrate to help quickly and more with minimal human intervention respond to threats thereby also reducing the time it takes to respond to threats. However, issues like quality of the data used in the model, reliability of the algorithm besides, question marks like who will tamper with the AI systems. The review also discusses new trends in cyber defense and remediation that may be of interest in the future, namely continuous authentication and advanced threat hunting. Potential issues associated with data privacy and algorithmic bigotry are pointed out as promising directions for future studies in this domain. Conclusion: The integration of AI, ML, and data analytics in cybersecurity represents a paradigm shift in how organizations approach digital defense. These technologies provide relevant functions for increasing threat diagnostics and response capabilities, as well as improving the predictive feature offered by this automation. The integration of AI, ML along with data analytics results into an architecture that is strong, flexible, intelligent and adaptive enough to cope up with growing security threats. Despite all these issues, including the problems with data quality and reliability of algorithms, as well as the numerous ethical questions, employing these technologies in cybersecurity seems promising. New types of cyber threats constantly emerge and therefore ongoing enhancement of AI and ML security tools will be imperative. The long-term research should endeavor to address the challenges mentioned above as well as elaborate on additional possible uses of these technologies in strengthening cybersecurity

SMARTCOPE: Smartphone Change Of Possession Evaluation for continuous authentication

The goal of continuous smartphone authentication is to detect when the adversary has gained possession of the user’s device post-login. This is achieved by triggering re-authentication at fixed, frequent intervals. However, these intervals do not take into account external information that might indicate that the impostor has gained physical access to the user’s device. Continuous smartphone authentication typically relies on behavioral cues, such as hand movement and touchscreen swipes, that can be collected without interrupting the user’s activity. Because these behavioral signals are characterized by relatively high error rates compared to physiological biometrics, their use at fixed intervals leads to unnecessary interruptions to the user’s activity in case of a false reject, and to not recognizing the impostor in case of a false accept.To address these issues, in this paper we introduce a novel framework called SMARTCOPE: Smartphone Change Of Possession Evaluation. In this work, SMARTCOPE leverages smartphone movement signals collected during user activity to determine when the smartphone is no longer in the hands of its owner. When this occurs, SMARTCOPE triggers re-authentication. By using these signals, we are able to reduce the total number of re-authentication points while simultaneously lowering re-authentication error rates. Our analysis shows that our technique can reduce equal error rates by over 40%, from 7.8% to 4.6% using movement and keystroke features. Further, we show that SMARTCOPE can be used to transform a static (login-time) authentication system, such as face recognition, to a continuous re-authentication system, with a significant increase in security and limited impact on usability.

Research on Network Security Situation Assessment Model in Decentralized Computing Environment

Abstract In this paper, decentralized computing is used as an entry point to review the latest research results on network security issues through two methods, namely task assignment and hierarchical analysis, and construct a network security posture assessment model based on decentralized computing. A control framework is constructed by utilizing the functional complementarity of continuous authentication and security threat assessment in order to facilitate real-time observation of the security situation of the network and timely elimination of malicious nodes. A quantitative network security threat posture assessment model is constructed through hierarchical analysis to observe the extent of the breach of confidentiality and integrity of network information based on the security threat posture index. The effectiveness of the network security posture assessment model and method proposed in this paper was verified by empirical analysis in a simulated environment. The results show that after the simulated attack lasts for 12 minutes, the network security risk index measured by the assessment model in the test cascade case becomes larger with the intensification of the network attack, and the risk index value is up to 5.5. In summary, the network security posture assessment model based on decentralized computing designed in this paper can quickly reflect the changes in the security status of the underlying network and provide administrators with the current security status of the network in a macroscopic way.

Pattern unlocking guided multi‐modal continuous authentication for smartphone with multi‐branch context‐aware representation learning and auto encoder

AbstractWidely accepted explicit authentication protocols are vulnerable to a series of attacks, for example, shoulder surfing and smudge attacks, leaving users with the constant burden of periodic password changes. As such, we propose a novel framework for continuous authentication on smartphones. This approach is guided by pattern unlocking, which is widely used and will not cause learning cost. After collecting multi‐modal data that describe both behavioral and contextual information, we employ a multi‐branch context‐aware attention network as the representation learner to perform feature extraction, then an auto encoder is then used for authentication. To overcome challenges, including cold‐start and few‐shot training, which is less discussed in other works, we incorporate transfer learning with a coarse‐to‐fine pre‐training workflow. Additionally, we deploy a hierarchical approach to offload model tuning overhead from smartphones. Extensive experiments on more than 68 000 real‐world recordings validate the effectiveness of the proposed method, with an EER (equal error rate) of 2.472% under mixed contexts, which consistently outperforms state‐of‐the‐art approaches under both static and mixed contexts.

User Verification Using Evoked EEG by Invisible Visual Stimulation

Person authentication using biometric information has recently become popular among researchers. User management based on biometrics is more reliable than that using conventional methods. To secure private information, it is necessary to build continuous authentication-based user management systems. Brain waves are suitable biometric modalities for continuous authentication. This study is based on biometric authentication using brain waves evoked by invisible visual stimuli. Invisible visual stimulation is considered over visual stimulation to overcome the obstacles faced by a user when using a system. Invisible stimuli are confirmed by changing the intensity of the image and presenting high-speed stimulation. To ensure invisibility, stimuli of different intensities were tested, and the stimuli with an intensity of 5 % was confirmed to be invisible. To improve the verification performance, a continuous wavelet transform was introduced over the Fourier transform because it extracts both time and frequency information from the brain wave. The scalogram obtained by the wavelet transform was used as an individual feature and for synchronizing the template and test data. Furthermore, to improve the synchronization performance, the waveband was split based on the power distribution of the scalogram. A performance evaluation using 20 subjects showed an equal error rate of 3.8 %.

Blockchain-Based Multistage Continuous Authentication for Smart Devices

Blockchain-Based Multistage Continuous Authentication for Smart Devices

PC-based User Continuous Authentication System Using the User's Finger Stroke Characteristics

Biometric technology, which performs continuous authentication based on user behavior, has been developed in various ways depending on the type of device, input device, and sensor. Research on continuous authentication technology in PC-based systems with few sensors installed is based on data from 3physical devices that extract and analyze features from keyboard and mouse input patterns. Among these, previous studies on continuous authentication through keyboard input performed continuous authentication using the key hold delay time that occurs when one key is pressed, the key interval delay time that occurs due to the interaction between fingers, and the key press delay time. did However, the keyboard-based continuous authentication model has limitations in increasing accuracy due to a small number of features. Therefore, in this paper, when a user inputs a sentence using a QWERTY keyboard in a PC system, the function is subdivided by reflecting the characteristics of each finger and used for continuous authentication. The features extracted by reflecting the characteristics of the finger were subdivided into a total of 151 latencies, and SVDD, decision tree, and CNN were used as continuous authentication models. Experimental data was collected through the user's input of randomly displayed sentences, and features were created based on this. User keystroke behavior was used to validate the continuous authentication model. Validation metrics included thresholds for classification accuracy (ACC), ROC curves, false rejection rate (FRR), equal error rate (EER), and false acceptance rate (FAR). As a result of the experiment, it was found that continuous authentication including the user's finger input pattern was superior to the existing method.

A Review of User Identification Methods Based on Digital Fingerprint

Methods of user identification based on digital fingerprints are considered. The main approaches for the browser fingerprints creation which is installed on the user's device and characterizes the device belonging to the user are presented. The methods used to identify a person (user) during the operation of the device are also described. Methods using both the dynamics of keystrokes and interactions with the touch screen, voice and geolocation data, as well as behavioral biometrics and behavioral profile are presented. The concept of continuous authentication is described as a development of the identification approach. A list of publicly available data sets mentioned in the studies reviewed in the review is provided, with links to download them.

Analysis of Continuous Authentication Technique Involving Combined Iris and Periocular Biometrics in A Metaverse Environment

Analysis of Continuous Authentication Technique Involving Combined Iris and Periocular Biometrics in A Metaverse Environment

CGAPP: A continuous group authentication privacy-preserving platform for industrial scene

In Industry 4.0, security begins with the workers’ authentication, which can be done individually or in groups. Recently, group authentication is gaining momentum, allowing users to authenticate as group members without the need to specify the particular individual. Continuous authentication and federated learning are promising techniques that might help group authentication by providing privacy, by its own design, and extra security compared to traditional methods based on passwords, tokens, or biometrics. However, these techniques have not previously been combined or evaluated for authenticating workers in Industry 4.0. Thus, this paper proposes a novel continuous group authentication privacy-preserving (CGAPP)platform that is suitable for the industry. The CGAPP platform incorporates statistical data from workers’ smartphones and employs federated learning-based outlier detection for group worker authentication while ensuring the privacy of personal data vectors. A series of experiments were performed to measure the framework’s suitability and address the following research questions: (i) What is the cost of using FL compared to full data access in industrial scenarios? (ii) How robust is federated learning against adversarial attacks, specifically, how much malicious data is required to deceive the model? and (iii) How much noise is required to disrupt the authentication system? The results demonstrate the effectiveness of the CGAPP platform in the industry since it provides factory safety while preserving privacy. This platform achieves an accuracy of 92%, comparable to the 96% obtained by traditional approaches in the literature that do not address privacy concerns. The platform’s robustness is tested against attacks in the second and third experiments, and various countermeasures are evaluated. While the CGAPP platform exhibits certain vulnerabilities to data injection attacks, straightforward countermeasures can alleviate them. Nevertheless, the system’s performance experiences a notable impact in the event of a data perturbation attack, and the countermeasures investigated are ineffective in addressing this issue.

Adaptive Deep Feature Fusion for Continuous Authentication With Data Augmentation

Mobile devices are becoming increasingly popular and are playing significant roles in our daily lives. Insufficient security and weak protection mechanisms, however, cause serious privacy leakage of the unattended devices. To fully protect mobile device privacy, we propose ADFFDA, a novel mobile continuous authentication system using an Adaptive Deep Feature Fusion scheme for effective feature representation, and a transformer-based GAN for Data Augmentation, by leveraging smartphone built-in sensors of the accelerometer, gyroscope and magnetometer. Given the normalized sensor data, ADFFDA utilizes the transformer-based GAN consisting of a transformer-based generator and a CNN-based discriminator to augment the training data for CNN training. With the augmented data and the especially designed CNN based on the ghost module and ghost bottleneck, ADFFDA extracts deep features from the three sensors by the trained CNN, and exploits an adaptive-weighted concatenation method to adaptively fuse the CNN-extracted features. Based on the fused features, ADFFDA authenticates users by using the one-class SVM (OC-SVM) classifier. We evaluate the authentication performance of ADFFDA in terms of the efficiency of the transformer-based GAN, GAN-based data augmentation, CNN architecture, adaptive-weighted feature fusion, and OC-SVM classifier. The experimental results show that ADFFDA obtains the best authentication performance w.r.t representative approaches, by achieving a mean equal error rate of 0.01%.