Search Results (35)

Traditional authentication systems rely mainly on static login checkpoints such as passwords or one-time verification. However, the expansion of cloud services, mobile devices, and distributed digital platforms has exposed significant limitations in these approaches. Modern cyberattacks increasingly exploit credential theft, phishing, and session hijacking in order to bypass login-based security mechanisms. This study examines the use of behavioral biometrics and data-driven analytics in continuous authentication systems that verify user identity throughout an active session. Behavioral interaction signals such as keystroke dynamics, cursor movement patterns, touchscreen gestures, and device usage characteristics can form distinctive behavioral profiles for individual users. Machine-learning models can analyze these signals to detect deviations from established behavioral patterns that may indicate unauthorized access. The paper develops a conceptual framework for continuous behavioral authentication that integrates behavioral monitoring, anomaly detection, and scalable data-processing infrastructures. The analysis highlights both the cybersecurity benefits of behavioral authentication and the challenges related to large-scale behavioral data collection, including privacy protection and responsible data governance. Full article

Post-login threats such as device sharing and session takeover motivate continuous authentication with behavioral signals. This paper studies a lightweight keystroke-dynamics pipeline designed for strict cross-session evaluation and browser-side scoring. Using the fixed-text and free-text tracks of the public KeyRecs dataset, we extract compact repetition-level and sliding-window digraph-timing features and train per-user one-vs-rest Logistic Regression verifiers on Session 1 (S1). Thresholds are selected only on S1 and transferred unchanged to Session 2 (S2), preventing test-set tuning and exposing operating-point instability under session drift. Fixed-text achieves S2 AUC mean/median 0.895/0.918 with a half total error rate (HTER) around 0.19, while free-text reaches AUC mean/median 0.884/0.899 with a similar transferred-threshold HTER. Personal thresholds and a pooled-S1 global threshold perform similarly on average, suggesting that global thresholding can simplify deployment without replacing per-user scoring models. A scaler-only warm-up update yields limited and inconsistent gains, showing that mean/variance adaptation alone is insufficient. Finally, compact JSON artifacts and replay-based browser benchmarks demonstrate deterministic client-side scoring with very small per-sample latency. Overall, the results show that useful threshold-free separability does not by itself guarantee stable operating-point transfer under cross-session drift. Full article

A distinct typing interface using surface electromyography (sEMG) can facilitate silent, hands-free typing by interpreting muscle activity in relation to specific keystrokes. Character-level recognition poses greater challenges than coarse gesture recognition because it is sensitive to subtle temporal variations and overlapping muscle dynamics. Temporal features are essential for typing recognition because keypresses may differ in duration, force, and accompanying hand movements across users. This paper proposes TransTCNet, a two-stage deep neural network architecture with a causal convolutional layer for learning local features and a transformer-based component for learning long-range temporal interactions. We evaluated our network on a publicly available 26-class typing sEMG dataset acquired from 19 individuals. The model achieved a validation accuracy of 96.53%, exceeding the baseline models. Our study revealed generalization among participants, and the AUC values were also high (>0.994) across all classes. The model was highly reliable and exhibited high prediction confidence (>0.9), enabling us to achieve a high training accuracy (97.86%) for real-time filtering decisions. TransTCNet could be suitable for wearable and edge devices due to its efficient architecture and low inference cost. The model’s ability to consistently decode fine-grained neuromuscular signals across users makes it well-suited for real-time applications such as adaptive user interfaces, virtual and augmented reality, prosthetic control, and communication systems. Full article

Cyber coercion, where legitimate users are forced to perform actions under duress, poses a serious insider threat to modern organizations, especially to critical infrastructure. Traditional security controls and monitoring tools struggle to distinguish coerced actions from normal user actions. In this paper, we propose a cyber coercion detection system that analyzes a user’s activity using an integrated large language model (LLM) to evaluate contextual cues from user commands or actions and current policies and procedures. If the LLM indicates coercion, behavioral methods, such as keystroke dynamics and mouse usage patterns, and physiological signals such as heart rate are analyzed to detect stress or anomalies indicative of duress. Experimental results show that the LLM-assisted multimodal approach shows potential in detecting coercive activity with and without detected coercive communication, where multimodal biometrics assist the confidence of the LLM in cases in which it does not detect coercive communication. The proposed system may add a critical detection capability against coercion-based cyber-attacks, providing early warning signals that could inform defensive responses before damage occurs. Full article

Traditional user authentication mechanisms in information systems, such as passwords and biometrics, remain vulnerable to forgery, theft, and privacy breaches. To address these limitations, this study proposes a two-factor authentication framework that integrates Channel State Information (CSI) with conventional methods to enhance security and reliability. The proposed approach leverages unique CSI variations induced by user-specific keystroke dynamics to extract discriminative biometric features. A robust signal processing pipeline is implemented, combining Hampel filtering, Butterworth low-pass filtering, and wavelet transform threshold denoising to eliminate noise and outliers from raw CSI data. Feature extraction is further optimized through a dual-threshold moving window detection algorithm for precise activity segmentation, a subcarrier selection method to filter redundant or unstable channels, and principal component analysis (PCA) to reduce feature dimensionality while retaining 90% of critical information. For classification, a kernel support vector machine (SVM) model is trained using a randomized hyperparameter search algorithm. The SVM classifies the CSI feature patterns obtained from user-specific keystroke dynamics, which are processed by Hampel filtering, Butterworth low-pass filtering, wavelet transform threshold denoising, a dual-threshold moving window detection algorithm, a subcarrier selection method, and PCA, to achieve optimal performance. The experimental results show that the user recognition accuracy of this algorithm is 2–3% better than current algorithms. Full article

Background: Keystroke dynamics authentication is a behavioral biometric method that verifies user identity by analyzing typing patterns. While traditional machine learning methods (e.g., decision trees, SVM) have shown potential in this field, their performance suffers in real-world scenarios due to data imbalance and limited recognition of certain classes, undermining system security and reliability. Methods: To address these issues, this study combines the Synthetic Minority Over-sampling Technique (SMOTE) with ensemble learning methods to improve classification accuracy. A Django-based platform was developed for standardized keystroke data collection, generating a balanced dataset to evaluate various classifiers. Experiments: Experiments were conducted using both the Django-collected dataset and the CMU benchmark dataset to compare traditional classifiers with SMOTE-enhanced ensemble learning models, such as Random Forest, XGBoost, and Bagging, on metrics like accuracy, recall, G-mean, and F1-score. Conclusions: The results show that SMOTE-enhanced ensemble learning models significantly outperform traditional classifiers, particularly in detecting minority classes. This approach effectively addresses data imbalance, improving model robustness and security, and provides a practical reference for building more reliable keystroke dynamics authentication systems. Full article

Keystroke dynamics is the field of computer science that exploits data derived from the way users type. It has been used in authentication systems, in the identification of user characteristics for forensic or commercial purposes, and to identify the physical and mental state of users for purposes that serve human–computer interaction. Studies of keystroke dynamics have used datasets created from volunteers recording fixed-text typing or free-text typing. Unfortunately, there are not enough keystroke dynamics datasets available on the Internet, especially from the free-text category, because they contain sensitive and personal information from the volunteers. In this work, a free-text dataset is presented, which consists of 533 logfiles, each of which contains data from 3500 keystrokes, coming from 164 volunteers. Specifically, the software developed to record user typing is described, the demographics of the volunteers who participated are given, the structure of the dataset is analyzed, and the experiments performed on the dataset justify its utility. Full article

In an era marked by escalating concerns about digital security, biometric identification methods have gained paramount importance. Despite the increasing adoption of biometric techniques, keystroke dynamics analysis remains a less explored yet promising avenue. This study highlights the untapped potential of keystroke dynamics, emphasizing its non-intrusive nature and distinctiveness. While keystroke dynamics analysis has not achieved widespread usage, ongoing research indicates its viability as a reliable biometric identifier. This research builds upon the existing foundation by proposing an innovative deep-learning methodology for keystroke dynamics-based identification. Leveraging open research datasets, our approach surpasses previously reported results, showcasing the effectiveness of deep learning in extracting intricate patterns from typing behaviors. This article contributes to the advancement of biometric identification, shedding light on the untapped potential of keystroke dynamics and demonstrating the efficacy of deep learning in enhancing the precision and reliability of identification systems. Full article

User-generated passwords often pose a security risk in authentication systems. However, providing a comparative substitute poses a challenge, given the common tradeoff between security and user experience. This paper integrates cryptographic methods (both asymmetric and symmetric), steganography, and a combination of physiological and behavioural biometrics to construct a prototype for a passwordless authentication system. We demonstrate the feasibility of scalable passwordless authentication while maintaining a balance between usability and security. We employ threat modeling techniques to pinpoint the security prerequisites for the system, along with choosing appropriate cryptographic protocols. In addition, a comparative analysis is conducted, examining the security impacts of the proposed system in contrast to that of traditional password-based systems. The results from the prototype indicate that authentication is possible within a timeframe similar to passwords (within 2 s), without imposing additional hardware costs on users to enhance security or compromising usability. Given the scalable nature of the system design and the elimination of shared secrets, the financial and efficiency burdens associated with password resets are alleviated. Furthermore, the risk of breaches is mitigated as there is no longer a need to store passwords and/or their hashes. Differing from prior research, our study presents a pragmatic design and prototype that deserves consideration as a viable alternative for both password-based and passwordless authentication systems. Full article

This research article delves into the development of a reinforcement learning (RL)-based continuous authentication system utilizing behavioral biometrics for user identification on computing devices. Keystroke dynamics are employed to capture unique behavioral biometric signatures, while a reward-driven RL model is deployed to authenticate users throughout their sessions. The proposed system augments conventional authentication mechanisms, fortifying them with an additional layer of security to create a robust continuous authentication framework compatible with static authentication systems. The methodology entails training an RL model to discern atypical user typing patterns and identify potentially suspicious activities. Each user’s historical data are utilized to train an agent, which undergoes preprocessing to generate episodes for learning purposes. The environment involves the retrieval of observations, which are intentionally perturbed to facilitate learning of nonlinear behaviors. The observation vector encompasses both ongoing and summarized features. A binary and minimalist reward function is employed, with principal component analysis (PCA) utilized for encoding ongoing features, and the double deep Q-network (DDQN) algorithm implemented through a fully connected neural network serving as the policy net. Evaluation results showcase training accuracy and equal error rate (EER) ranging from 94.7% to 100% and 0 to 0.0126, respectively, while test accuracy and EER fall within the range of approximately 81.06% to 93.5% and 0.0323 to 0.11, respectively, for all users as encoder features increase in number. These outcomes are achieved through RL’s iterative refinement of rewards via trial and error, leading to enhanced accuracy over time as more data are processed and incorporated into the system. Full article

As artificial intelligence has evolved, deep learning models have become important in extracting and interpreting complex patterns from raw multidimensional data. These models produce multidimensional embeddings that, while containing a lot of information, are often not directly understandable. Dimensionality reduction techniques play an important role in transforming multidimensional data into interpretable formats for decision support systems. To address this problem, the paper presents an analysis of dimensionality reduction and visualization techniques that embrace complex data representations and are useful inferences for decision systems. A novel framework is proposed, utilizing a Siamese neural network with a triplet loss function to analyze multidimensional data encoded into images, thus transforming these data into multidimensional embeddings. This approach uses dimensionality reduction techniques to transform these embeddings into a lower-dimensional space. This transformation not only improves interpretability but also maintains the integrity of the complex data structures. The efficacy of this approach is demonstrated using a keystroke dynamics dataset. The results support the integration of these visualization techniques into decision support systems. The visualization process not only simplifies the complexity of the data, but also reveals deep patterns and relationships hidden in the embeddings. Thus, a comprehensive framework for visualizing and interpreting complex keystroke dynamics is described, making a significant contribution to the field of user authentication. Full article

The rapid development of information and communication technologies and the widespread use of the Internet has made it imperative to implement advanced user authentication methods based on the analysis of behavioural biometric data. In contrast to traditional authentication techniques, such as the simple use of passwords, these new methods face the challenge of authenticating users at more complex levels, even after the initial verification. This is particularly important as it helps to address risks such as the possibility of forgery and the disclosure of personal information to unauthorised individuals. In this study, the use of keystroke dynamics has been chosen as a biometric, which is the way a user uses the keyboard. Specifically, a number of Bulgarian-speaking users have been recorded during their daily keyboard use, and then a system has been implemented which, with the help of machine learning models, recognises certain acquired or intrinsic characteristics in order to reveal part of their identity. The results show that users can be categorised using keystroke dynamics, in terms of the age group they belong to and in terms of their educational level, with high accuracy rates, which is a strong indication for the creation of applications to enhance user security and facilitate their use of Internet services. Full article

Keystroke dynamics is a biometric method that uses a subject’s typing patterns for authentication or identification. In this paper we investigate typing language as a factor influencing an individual’s keystroke dynamics. Specifically, we discern whether keystroke dynamics is contingent on the spatial arrangement of letters on the keyboard, or alternatively, whether it is influenced by the linguistic characteristics inherent to the language being used. For this purpose, we construct a new dataset called the Bilingual Keystroke Dynamics Dataset in two languages: English and Arabic. The results show that the authentication system is not contingent on the spatial arrangement of the letters, and is primarily influenced by the language being used, and a system that is used by bilingual users must take into account that each user should have two profiles created, one for each language. An average equal error rate of 0.486% was achieved when enrolling in English and testing on Arabic, and 0.475% when enrolling in Arabic and testing on English. Full article

Keystroke authentication is a well-established biometric technique that has gained significant attention due to its non-intrusive and continuous characteristics. The method analyzes the unique typing patterns of individuals to verify their identity while interacting with the keyboard, both virtual and hardware. Current deep-learning approaches like TypeNet and TypeFormer focus on generating biometric signatures as embeddings for the entire typing sequence. The authentication process is defined using the Euclidean distances between the new typing embedding and the saved biometric signatures. This paper introduces a novel approach called DoubleStrokeNet for authenticating users through keystroke analysis using bigram embeddings. Unlike conventional methods, our model targets the temporal features of bigrams to generate user embeddings. This is achieved using a Transformer-based neural network that distinguishes between different bigrams. Furthermore, we employ self-supervised learning techniques to compute embeddings for both bigrams and users. By harnessing the power of the Transformer’s attention mechanism, the DoubleStrokeNet approach represents a significant departure from existing methods. It allows for a more precise and accurate assessment of user authenticity, specifically emphasizing the temporal characteristics and latent representations of bigrams in deriving user embeddings. Our experiments were conducted using the Aalto University keystrokes datasets, which include 136 million keystrokes from 168,000 subjects using physical keyboards and 63 million keystrokes acquired on mobile devices from 60,000 subjects. The DoubleStrokeNet outperforms the TypeNet-based authentication system using 10 enrollment typing sequences, achieving Equal Error Rate (EER) values of 0.75% and 2.35% for physical and touchscreen keyboards, respectively. Full article

Keystroke dynamics is a soft biometric based on the assumption that humans always type in uniquely characteristic manners. Previous works mainly focused on analyzing the key press or release events. Unlike these methods, we explored a novel visual modality of keystroke dynamics for human identification using a single RGB-D sensor. In order to verify this idea, we created a dataset dubbed KD-MultiModal, which contains 243.2 K frames of RGB images and depth images, obtained by recording a video of hand typing with a single RGB-D sensor. The dataset comprises RGB-D image sequences of 20 subjects (10 males and 10 females) typing sentences, and each subject typed around 20 sentences. In the task, only the hand and keyboard region contributed to the person identification, so we also propose methods of extracting Regions of Interest (RoIs) for each type of data. Unlike the data of the key press or release, our dataset not only captures the velocity of pressing and releasing different keys and the typing style of specific keys or combinations of keys, but also contains rich information on the hand shape and posture. To verify the validity of our proposed data, we adopted deep neural networks to learn distinguishing features from different data representations, including RGB-KD-Net, D-KD-Net, and RGBD-KD-Net. Simultaneously, the sequence of point clouds also can be obtained from depth images given the intrinsic parameters of the RGB-D sensor, so we also studied the performance of human identification based on the point clouds. Extensive experimental results showed that our idea works and the performance of the proposed method based on RGB-D images is the best, which achieved $99.44\%$ accuracy based on the unseen real-world data. To inspire more researchers and facilitate relevant studies, the proposed dataset will be publicly accessible together with the publication of this paper. Full article