Search

Feedback is important to improve writing quality; however, to provide timely and personalized feedback is a time-intensive task. Currently, most literature focuses on providing (human or machine) support on product characteristics, especially after a draft is submitted. However, this does not assist students who struggle during the writing process. Therefore, in this study, we investigate the use of keystroke analysis to predict writing quality throughout the writing process. Keystroke data were analyzed from 126 English as a second language learners performing a timed academic summarization task. Writing quality was measured using participants’ final grade. Based on previous literature, 54 keystroke features were extracted. Correlational analyses were conducted to identify the relationship between keystroke features and writing quality. Next, machine learning models (regression and classification) were used to predict final grade and classify students who might need support at several points during the writing process. The results show that, in contrast to previous work, the relationship between writing quality and keystroke data was rather limited. None of the regression models outperformed the baseline, and the classification models were only slightly better than the majority class baseline (highest AUC = 0.57). In addition, the relationship between keystroke features and writing quality changed throughout the course of the writing process. To conclude, the relationship between keystroke data and writing quality might be less clear than previously posited.

User authentication plays a critical role in access control of a man-machine system, where the knowledge factor like a Personal Identification Number (PIN) constitutes the most widely-used authentication element. However, knowledge factors are usually vulnerable to the spoofing attack. Recently, the inheritance factor like fingerprints emerges as an efficient alternative resilient to malicious users, but it normally requires special equipment. To this end, we propose WiPass, a device-free authentication system only leveraging the pervasive WiFi infrastructure to explore keystroke dynamics (manner and rhythm of keystrokes) captured by the Channel State Information (CSI) to recognize legitimate users while rejecting spoofers. However, it remains an open challenge to characterize the behavioral features hidden in the human subtle motions like keystrokes. Therefore, we build a signal enhancement model using Ricean distribution to amplify user keystroke dymanics and a hybrid learning model for user authentication, which consists of two parts, i.e., CNN-based feature extraction and SVM-based classification. The former relies on visualizing the channel responses into time-series images to learn the behavioral features of keystrokes in energy and spectrum domains, while the latter exploits such behavioral features for user authentication. We prototype WiPass on the low-cost off-the-shelf WiFi devices and verify its performance. Empirical results show that WiPass achieves on average 92.1% authentication accuracy, 5.9% false accept rate, and 6.3% false reject rate in three real environments.

Keyboard acts as one of the most commonly used mediums for human-computer interaction. Today, massive Internet of Things (IoT) devices are designed without a physical keyboard as they go tiny, but are almost all equipped with a wireless module for networks. In this work, we aim to enable a universal virtual keyboard using wireless signals, which would allow a typing interface for tiny IoT devices or serve as a portable alternative to the unwieldy physical keyboards. To this end, we present mmKey, the first universal virtual keyboard system using a single millimeter-wave (mmWave) radio. By leveraging the unique advantages of mmWave signals, mmKey converts any flat surface, with a printed paper keyboard, into an effective typing medium. mmKey enables concurrent keystrokes and supports multiple keyboard layouts (e.g., computer keyboard, piano keyboard, or phone keypad). We design a novel signal processing pipeline to detect, segment and separate, and finally recognize keystrokes. mmKey does not need any training except for a minimal one-time effort of only three key-presses for keyboard calibration upon the initial setup. We prototype mmKey using a commodity 802.11ad/ay chipset, customized to support radar-like operations, and evaluate it with different keyboard layouts under various settings. Experimental results with 10 participants demonstrate a keystroke recognition accuracy of > 95% for single-key case and > 90% for multi-key scenario, which leads to a word recognition accuracy of > 97%.

As an emerging technology, industrial Internet of Things (IIoT) connects massive sensors and actuators to empower industrial sectors being smart, autonomous, efficient, and safety. However, due the large number of build-in sensors of IIoT smart devices, the IIoT systems are vulnerable to side-channel attack. In this article, a novel side-channel-based passwords cracking system, namely MAGLeak, is proposed to recognize the victim's passwords by leveraging accelerometer, gyroscope, and magnetometer of IIoT touch-screen smart device. Specifically, an event-driven data collection method is proposed to ensure that the user's keystroke behavior can be reflected accurately by the obtained measurements of three sensors. Moreover, random forest algorithm is leveraged for the recognition module, followed by a data preprocessing process. Extensive experimental results demonstrate that MAGLeak achieves a high recognition accuracy under small training dataset, e.g., achieving recognition accuracy 98% of each single key for 2000 training samples.

In the era of information technology, secure access to electronic systems is important for protecting private information. Among various authentication techniques, keystroke authentication methods based on users’ touch behavior have received increasing attention. In this paper, we present a technique for obtaining high multi-user authentication accuracy by utilizing users’ touch time and force information, which were obtained from a piezoelectric touch panel. After feeding a support vector machine (SVM) with users’ touch features, a high classification accuracy of 97% is achieved, validating the feasibility of the proposed technique for achieving highly secure multi-user authentication, hence advancing the development of security techniques.

El mantenimiento es una de las principales estrategias que se aplican en la industria para mantener la continuidad, seguridad, eficacia de los procesos productivos. En este sentido, es imperativo establecer estrategias para mejorar o diseñar los planes de mantenimiento, esto debe hacerse jerarquizando los procesos, sistemas y equipos del proceso productivo. Esto se conoce como análisis de criticidad. El objetivo de este trabajo fue realizar un análisis de criticidad del equipamiento industrial de la línea de bovinos del centro de faenamiento de la ciudad de Portoviejo, Ecuador. Para ello, se conocieron las condiciones del equipamiento industrial y posteriormente se determinó su criticidad. Los resultados mostraron que el centro de faenamiento no posee de un plan de mantenimiento preventivo para el equipamiento industrial, siendo las labores de tipo correctivo, y que los equipos con mayor criticidad son el tecle del izado, tecle para rayado y corte de patas posteriores, sierra eléctrica de cortar canal, sierra de cortar esternón, tecle de descuerado y el noqueador neumático, esto como consecuencia de la frecuencia de fallas presentadas, impacto en la seguridad y costos de mantenimiento. Se sugirió el diseño de un plan de mantenimiento preventivo para los equipos con alta y media criticidad. Palabras clave: bovinos, criticidad, equipos, faenamiento, mantenimiento.

Alphanumerical usernames and passwords are the most used computer authentication technique. This approach has been found to have a number of disadvantages. Users, for example, frequently choose passwords that are simple to guess. On the other side, if a password is difficult to guess, it is also difficult to remember. Graphical passwords have been proposed in the literature as a potential alternative to alphanumerical passwords, based on the fact that people remember pictures better than text. Existing graphical passwords, on the other hand, are vulnerable to a shoulder surfing assault. To address this shoulder surfing vulnerability, this study proposes an authentication system for web-applications based on visual cryptography and cued click point recall-based graphical password. The efficiency of the proposed system was validated using unit, system and usability testing measures. The results of the system and unit testing showed that the proposed system accomplished its objectives and requirements. The results of the usability test showed that the proposed system is easy to use, friendly and highly secured.

Biometrics are physical or behavioral human characteristics that can be used to identify a person. It is widely known that keystroke or typing dynamics for short, fixed texts (e.g., passwords) could serve as a behavioral biometric. In this study, we investigate whether keystroke data from essay responses can lead to a reliable biometric measure, with implications for test security and the monitoring of writing fluency and style changes. Based on keystroke data collected from a high-stakes writing testing setting, we established a preliminary biometric benchmark for detecting test-taker identity by using features extracted from their writing process logs. We report a benchmark keystroke biometric accuracy of equal error rate of 4.7% for identifying same versus different individuals on an essay task. In particular, we show that the inclusion of writing process features (e.g., features designed to describe the writing process) in addition to the widely used typing-timing features (e.g., features based on the time intervals between two-letter key sequences) improves the accuracy of the keystroke biometrics. The proposed keystroke biometrics can have important implications for the writing assessments administered through the remotely proctored tests that have been widely adopted during the COVID pandemic. © 2021 Educational Testing Service

With the recent advancement of smartphone technology in the past few years, smartphone usage has increased on a tremendous scale due to its portability and ability to perform many daily life tasks. As a result, smartphones have become one of the most valuable targets for hackers to perform cyberattacks, since the smartphone can contain individuals’ sensitive data. Smartphones are embedded with highly accurate sensors. This article proposes BetaLogger , an Android-based application that highlights the issue of leaking smartphone users’ privacy using smartphone hardware sensors (accelerometer, magnetometer, and gyroscope). BetaLogger efficiently infers the typed text (long or short) on a smartphone keyboard using Language Modeling and a Dense Multi-layer Neural Network (DMNN). BetaLogger is composed of two major phases: In the first phase, Text Inference Vector is given as input to the DMNN model to predict the target labels comprising the alphabet, and in the second phase, sequence generator module generate the output sequence in the shape of a continuous sentence. The outcomes demonstrate that BetaLogger generates highly accurate short and long sentences, and it effectively enhances the inference rate in comparison with conventional machine learning algorithms and state-of-the-art studies.

“Literal translation” is a popular construct in Translation Studies. Research from computational approaches has consistently shown that non-literal translations, i.e., renderings semantically and syntactically different or not close to the source text, are more difficult or effortful to produce than literal ones. This paper researches whether literal translations are systematically less effortful to process than non-literal ones using comparable corpus data. The effort incurred in processing literal translations from a parallel corpus is compared to that of processing the most frequent non-literal renderings found in previous comparable corpus studies. Ten professional translators edited a text using a mock translation environment setup using the keylogger Inputlog. The task was presented as a regular editing process with a full cohesive text presented segment pair by segment pair. Time served as a proxy for overall cognitive effort. We analyzed time from presentation to type (TTP) and time to completion of segment edit (TC), or complete editing events. Results showed that processing efforts are indistinguishable between categories, suggesting that cognitive effort to edit non-literal default translation candidates is not always higher when compared to the most frequent literal translations from a parallel corpus.

User authentication is the first and most critical step in protecting a man–machine system from a malicious spoofer. However, security and privacy are just like the two sides of one coin, hard to see both at the same time, especially by the current mainstream credential- and biometric-based approaches. To this end, we propose WiONE, a safe and privacy-preserving user authentication system leveraging the ubiquitous Wi-Fi infrastructure by exploring “ how you behave ” rather than “ who you are ”. The key idea is to apply deep learning to user physical behavior captured by Wi-Fi channel state information (CSI) to identify legitimate users while rejecting spoofers. The design of WiONE faces two challenges, namely, how to capture the subtle behavior, such as a keystroke on CSI, and how to mitigate the heavy environment-specific training required by deep learning. For the former, we design a behavior enhancement model based on the Rician fading to highlight the behavior-induced information by suppressing the behavior-unrelated information on channel response. For the latter, we develop a behavior characterization method tailored for the prototypical networks to facilitate the extraction of the domain-independent behavioral features and enable one-shot recognition of a new user in a new environment. Numerous experiments are conducted in several real-world environments, and the results show that WiONE outperforms its state-of-the-art rivals in authentication performance with much less training effort.

У статті запропоновано методику виявлення несанкціонованих обчислювальних процесів інформаційнотелекомунікаційних систем. Існуючі технології виявлення APT атак засновані на процедурах багаторівневого аналізу великого масиву даних про різноманітні поточні події в ІТС. Ці дані збираються в електронних журналах подій. Очевидно, що модель APT атаки повинна дозволяти пов’язувати події за часом і в просторі. Комплекси програм, які наповнюють інформацією журнали і реалізують автоматизовані технології їх аналізу, відомі як системи SIEM. У свою чергу, технології автоматизованого аналізу подій засновані на моделях атак. Шаблон APT атаки – це набір взаємопов’язаних подій. Порівняння такого шаблону і поточних подій становить суть процесу оцінки в рамках SIEM. Основним завданням методики є автоматизація процесу виявлення несанкціонованих дій, прийняття рішення про наявність APT атаки, та реалізацію методів захисту від неї. Основу APT атаки становить комплекс дій, що реалізуються в різних компонентах ІТС на тривалому відрізку часу. З позицій політики безпеки такі події окремо можуть нести легальний характер. Розглянуто програмні та апаратні засоби, призначені для прихованого спостереження за діяльністю користувачів інформаційно-телекомунікаційних систем. Санкціоновані моніторингові програмні продукти використовуються адміністраторами безпеки інформаційно-телекомунікаційних систем для забезпечення моніторингу. Детально розглянуто застосування для прихованого моніторингу активних процесів інформаційно-телекомунікаційних систем. Запропоновано використати в якості прикладу несанкціонованого обчислювального процесу програмні та апаратні кейлоггери. Детально описано методи захисту від них. Отримані результати доцільно направити на удосконалення методів виявлення несанкціонованих обчислювальних процесів інформаційно-телекомунікаційних систем.

Modern society is far more dependent on electronic devices than the previous generations. This dependency has both pros and cons. Although the list of pros is endless, they can easily be outweighed by one con which is being vulnerable to malicious programs. Keylogger is one such malware. Earlier, the prime focus was just limited to recording keystrokes made by a user but now are known for incorporating a multitude of features. Keyloggers are used to steal confidential information covertly and their detection is not quite simple since they execute completely in stealth mode. In this exposition, an advanced software keylogger is proposed which is compared with the existing keyloggers based on two criteria, first being the number of features incorporated and second, the CPU usage while the keylogger is being executed. The evaluation posits that the proposed keylogger contains more features with keeping the CPU usage to a minimum hence making it difficult to be detected by the user.

Behavioural biometrics have the potential to provide an additional or alternative authentication mechanism to those involving a shared secret (i.e. a password). Keystroke timings are the focus of this study, where key press and release timings are acquired whilst monitoring a user typing a known phrase. Many studies exist in keystroke biometrics, but there is an absence of literature aiming to understand the relationship between characteristics of password policies and the potential of keystroke biometrics. Furthermore, benchmark datasets used in keystroke biometric research do not enable useful insights into the relationship between their capability and password policy. Herein, substitutions of uppercase, numeric, special characters, and their combination of passwords derived from English words are considered. Timings for 42 participants for the same 40 passwords are acquired. A matching system using the Manhattan distance measure with seven different feature sets is implemented, culminating in an Equal Error Rate of between 6% and 11% and accuracy values between 89% and 94%, demonstrating comparable accuracy to other threshold‐based systems. Further analysis suggests that the best feature sets are those containing all timings and trigraph press to press. Evidence also suggests that phrases containing fewer characters have greater accuracy, except for those with special character substitutions.

This papers shows that attackers can leak data from isolated, air-gapped computers to nearby smartphones via covert magnetic signals. The proposed covert channel works even if a smartphone is kept inside a Faraday shielding case, which aims to block any type of inbound and outbound wireless communication (Wi-Fi, cellular, Bluetooth, etc.). Malware is implemented to control the magnetic fields emanating from the computer by regulating workloads on the CPU cores. Sensitive data such as encryption keys, passwords, or keylogging data is encoded and transmitted over the magnetic signals. A smartphone located near the computer receives the covert signals with its magnetic sensor. I present technical background, discuss signal generation, data encoding, and signal reception. The proposed covert channel works from a user-level process, without requiring special privileges, and can successfully operate from within an isolated virtual machine (VM).

This paper demonstrates the feasibility of a side-channel attack to infer keystrokes on touch screen leveraging an off-the-shelf smartphone. Although there exist some studies on keystroke eavesdropping attacks on touch screen, they are mainly direct eavesdropping attacks, i.e., require the device of victims compromised to provide side-channel information for the adversary, which are hardly launched in practical scenarios. In this work, we show the practicability of an indirect eavesdropping attack, $KeyListener$ K e y L i s t e n e r , which infers keystrokes on QWERTY keyboards of touch screen leveraging audio devices on a smartphone. We investigate the attenuation of acoustic signals, and find that a user's keystroke fingers can be localized through the attenuation of acoustic signals received by the microphones in the smartphone. We then utilize the attenuation of acoustic signals to localize each keystroke, and further analyze errors induced by ambient noises. To improve the accuracy of keystroke localization, $KeyListener$ K e y L i s t e n e r further tracks finger movements during inputs through phase change and Doppler effect to reduce errors of acoustic signal attenuation-based keystroke localization. In addition, a binary tree-based search approach is employed to infer keystrokes in a context-aware manner. The proposed keystroke eavesdropping attack is robust to various environments without the assistance of additional infrastructures. Extensive experiments demonstrate that the accuracy of keystroke inference in top-5 candidates can approach 90 percent with a top-5 error rate of around 6 percent, which is a strong indication of the possible user privacy leakage of inputs on QWERTY keyboard.

In this paper, we present an improved ring-type virtual keyboard scheme that can achieve impressive performance with only one smart ring on a finger of each hand. The smart ring integrates a 6-DoF Inertial Measurement Unit (IMU) and a 3-DoF magnetometer sensor for collecting motion data during typing. First, a new keyboard layout is designed, by changing the previous rectangular layout to an arc structure, this method increases the difference in attitude angle between adjacent keys, which greatly improved the keystroke recognition accuracy. Secondly, other than the attitude angle feature, we also adopt acceleration data, gyroscope data and magnetometer data to describe the subtle differences between different keystrokes motion. Then, feature importance evaluation and feature correlation analysis were used to select features with high contribution rate and low similarity to describe keystrokes. Finally, nine effective features were selected from the attitude angle and magnetometer data for the final keystroke recognition. By weighing the number of selected features, recognition speed and recognition accuracy of training models, the keystroke recognition speed can increase by nearly 4 times while ensuring 98.53% of the keystroke recognition accuracy. This new ring-type virtual keyboard input scheme has the advantages in portability, small volume, and lower cost over many existing human-computer interface methods.

Despite numerous efforts, developing an authentication scheme that offers strong security while offering memorability and usability remains a grand challenge. In this paper, we propose a textual-graphical hybrid authentication scheme that improves the security, memorability and usability inadequacies of existing authentication schemes. This has been achieved by combining a range of mechanisms together, in a novel manner, to address weaknesses of the existing security schemes. Firstly, two dynamically selectable modes of password entry (Easy Login, and Secure Login) provide a trade-off between usability and security, allowing the user to dynamically switch to any of these methods in real-time based on the security of the surrounding environment (e.g., secure home environment versus insecure public places) or the criticality of the user account (e.g., a bank account). The other mechanisms included a novel use of the drawmetric mechanism for setting the password to improve memorability, multistep authentication, a novel adaptation of one-time password (OTP) concept using a random selection of password elements, random placement of password elements in different steps, assigning random numbers to the password elements to increase security, and use of simple addition to improve security. We have implemented and analysed the proposed scheme for its security against brute-force attacks, dictionary, shoulder surfing, random guessing, phishing or forming, keystroke/mouse logger, and multiple recording attacks. We have also investigated its usability and memorability, reporting various trends of password elements used and the respective authentication times. Moreover, we have compared the proposed scheme with eight other well-known authentication schemes in terms of its resilience and authentication time. The results and analyses demonstrate the effectiveness of the proposed scheme. We believe that a range of novel methods introduced in this proposed scheme opens several doors for innovation in security techniques.

Emotion can be defined as a subject’s organismic response to an external or internal stimulus event. The responses could be reflected in pattern changes of the subject’s facial expression, gesture, gait, eye-movement, physiological signals, speech and voice, keystroke, and mouse dynamics, etc. This suggests that on the one hand emotions can be measured/recognized from the responses, and on the other hand they can be facilitated/regulated by external stimulus events, situation changes or internal motivation changes. It is well-known that emotion has a close relationship with both physical and mental health, usually affecting an individual’s and a team’s work performance, thus emotion recognition is an important prerequisite for emotion regulation towards better emotional states and work performance. The primary problem in emotion recognition is how to recognize a subject’s emotional states easily and accurately. Currently, there are a body of good research on emotion recognition from facial expression, gesture, gait, eye-tracking, and other physiological signals such as speech and voice, but they are all intrusive and obtrusive to some extent. In contrast, keystroke, mouse and touchscreen (KMT) dynamics data can be collected non-intrusively and unobtrusively as secondary data responding to primary physical actions, thus, this paper aims to review the state-of-the-art research on emotion recognition from KMT dynamics and to identify key research challenges, opportunities and a future research roadmap for referencing. In addition, this paper answers the following six research questions (RQs): (1) what are the commonly used emotion elicitation methods and databases for emotion recognition? (2) which emotions could be recognized from KMT dynamics? (3) what key features are most appropriate for recognizing different specific emotions? (4) which classification methods are most effective for specific emotions? (5) what are the application trends of emotion recognition from KMT dynamics? (6) which application contexts are of greatest concern?

This article explores the possibility of identifying mentally stored constructions in writing process data, that is, data that reproduce the process through which a text is written. The unit that serves as a basis for the identification of constructions is the burst of writing, which corresponds to a chunk of text produced between two pauses. Bursts are examined in L1 French and L2 English keylogging data from the Process Corpus of English in Education and their potential constructional status is considered.

In the relatively recent past, the analysis of keystroke dynamics for biometric recognition purposes has intrigued researchers, since practical evidences have shown differences in the typing behaviours of distinct subjects. This area of research has become even more appealing since the emergence and evolution of mobile smartphones, given their pervasiveness and intensive use in real‐life applications. In addition, unlike hard keyboards used with computers, mobile smartphones offer the possibility of exploiting embedded sensors to augment the information acquired when typing on their soft keyboards. This study discusses the state of the art of keystroke‐dynamics‐based automatic recognition system, exclusively when dealing with mobile devices, for both verification and identification purposes. In more details, the databases employed, the features selected, the methodologies implemented, and the performance achieved through the technological advances introduced in the last years, are here overviewed.

The widespread use of smartphones has brought great convenience to our daily lives, while at the same time we have been increasingly exposed to security threats. Keystroke security is essential to user privacy protection. In this paper, we present GazeRevealer, a novel side-channel based keystroke inference framework to infer sensitive inputs on smartphone from video recordings of victim's eye patterns captured from smartphone front camera. We observe that eye movements typically follow the keystrokes typing on the number-only soft keyboard during password input. By exploiting eye movement patterns, we are able to infer the passwords being entered. We propose a novel algorithm to extract sensitive eye images from video streams, and classify these images with Support Vector Classification. We also propose a novel classification enhancement algorithm to further improve classification accuracy. Compared with prior keystroke detection approaches, GazeRevealer does not require any external auxiliary devices, and it only relies on smartphone front camera. We evaluate the performance of GazeRevealer on several smartphones under different real-life usage scenarios. The results show that GazeRevealer achieves an inference rate of 77.89 percent for single key number and an inference rate of 84.38 percent for 6-digit password in the ideal case.

Keystroke logs provide a comprehensive record of observable writing processes. Previous studies examining the keystroke logs of young L1 English writers performing experimental writing tasks have i...

New security systems, methods or techniques need to have their performance evaluated in conditions that closely resemble a real-life situation. The effectiveness with which individual identity can be predicted in different scenarios can benefit from seeking a broad base of identity evidence. Many approaches to the implementation of biometric-based identification systems are possible, and different configurations are likely to generate significantly different operational characteristics. The choice of implementational structure is, therefore, very dependent on the performance criteria, which is most important in any particular task scenario. The issue of improving performance can be addressed in many ways, but system configurations based on integrating different information sources are widely adopted in order to achieve this. Thus, understanding how each data information can influence performance is very important. The use of similar modalities may imply that we can use the same features. However, there is no indication that very similar (such as keyboard and touch keystroke dynamics, for example) basic biometrics will perform well using the same set of features. In this paper, we will evaluate the merits of using a three-modal hand-based biometric database for user prediction focusing on feature selection as the main investigation point. To the best of our knowledge, this is the first thought-out analysis of a database with three modalities that were collected from the same users, containing keyboard keystroke, touch keystroke and handwritten signature. First, we will investigate how the keystroke modalities perform, and then, we will add the signature in order to understand if there is any improvement in the results. We have used a wide range of techniques for feature selection that includes filters and wrappers (genetic algorithms), and we have validated our findings using a clustering technique.

WiFi access points are sources of considerable security risks as the wireless signals have the potential to leak important private information such as passwords. This article examines the security issues posed by point-of-sale (POS) terminals which are widely used in WiFi-covered environments, such as restaurants, banks, and libraries. In particular, we envisage an attack model on passwords entered on POS terminals. We put forward the WiPOS, a password inference system based on wireless signals. Specifically, the WiPOS is a device-free system that uses two commercial off-the-shelf (COTS) devices to collect WiFi signals. Implementing a new keystroke segmentation algorithm and adopting support vector machine (SVM) classifiers with global alignment kernel (GAK), the WiPOS achieves improvement on both keystroke recognition and password prediction. The experimental results show that the WiPOS can achieve more than 73% accuracy for 6-digit password with the top 100 candidates. This article calls the community to take a closer look at the risks posed by the current ubiquitous WiFi devices.

One of the problems that require a solution in Massive Open Online Courses (MOOC) is the lack of identification and authentication of the students. Different investigations have been carried out through several navigation, physiological and behavioral methods, achieving different recognition scales. Biometric authentication by keystroke patterns (Ups&Downs) has been implemented in several MOOCs for the ease of the digital platforms of the offeror to solve the identification problem. The objective of this research is to analyze the independence of the keystroke tool of the other demographic, sociographic and behavioral variables within a MOOC, establishing an initial pattern, and two authentication measurements throughout the course. The results show that the keystroke is independent of the analyzed variables, and it is reliable to identify the students in qualitative tests with extension answers.

The accuracy of keystroke based authentication methods for computer networks users is determined by a number of factors, the main of which are: user classification algorithm, number of experiment participants with different keystroke experience, method of data entry and hardware platform on which authentication systems testing is performed. Another very important factor, namely, the kind of timing features of keystorke, on the basis of which user profiles are built, is very often not taken into account. In the first part of the work the different timing features of keystroke are analyzed. Three main classes are identified: timing features of keyboard monographs, timing features of consecutive keyboard events and integral features of typing. Given the accuracy of authentication and the required volume of training and authentication samples, 4 timing features of keyboard monographs (2 absolute and 2 relative) and 15 timing features of keyboard digraphs (3 absolute and 12 relative) were selected as experimental informative parameters of keystroke. In the second part of the work, the most informative timing features of the keystroke monographs and digraphs have been found using "Keystroke Dynamics Benchmark Data Set " and Orange software. The assumption of different informativeness of the keystroke monographs and digraphs timing features was experimentally confirmed. The most useful (provides the highest authentication accuracy) timing features of keystroke dynamics is relative features of keystroke time parameters, which contains a flight time.

In this paper, we propose enhanced continuous authentication by supplementing keystroke and mouse dynamics with wrist motion behaviors. Our method bridges the security gap when neither the mouse nor the keyboard is being used, such as during transitions from mouse to keyboard and vice versa, or during intermittent pauses when wrist movement is captured. Context-aware keystroke latency feature cell generation improves performance and solves latency fluctuation – different diagraphs have different latencies in different words. Based on two Random Forest Ensemble Classifiers (RFECs) recognizing the mouse and keystroke actions with corresponding wrist motions and one Sequential Sampling Analysis (SSA) or SSA Dynamic Trust Model (SSA-DTM), the identity of the user can be continuously verified no matter the operation mode — mouse clicking or keyboard typing. Experimental results, based on 44 subjects, show that the proposed approach can reach an FRR of 0.92% for genuine users and an FAR of 0 for attackers. The approach is shown to be more superior in efficient and timely authentications by making an authentication decision within only 35 mixed actions — mouse clicks or keystrokes, compared with conventional methods solely based on the mouse geometry and locomotion features or keystroke latency features.

An investigation is performed of individual behavioral characteristics of text input that are based on the keystroke dynamics using a virtual keyboard, and their application in the authentication of mobile device users. Key hold time, time between two consecutive keystrokes, and keystroke pressure are used as features to build a user model. A feature vector of a freely typed text is constructed by a user-adapting algorithm that divides digraphs into groups according to the pressing speed and the grouping of keys according to their functionality. Outliers are sought and corrected on the basis of quartiles with subsequent standardization of values. A fuzzy search for exceptions based on potential functions is used to solve the problem of classification when there are no examples of keystrokes by an attacker in a training sample. The resulting software, which consists of a custom Android system keyboard, is used for data collection and experimental assessment of the quality of the proposed approach to building a user behavioral model, proving its effectiveness. The software is also used to develop a prototype of a user authentication system that employs biometric characteristics of interaction with an onscreen keyboard to protect all applications on a mobile device that uses a standard system keyboard.

A multistage biometric verification system uses multiple biometrics and/or multiple biometric verifiers to generate a verification decision. The core of a multistage biometric verification system is reject option which allows a stage not to give a genuine/impostor decision when it is not confident enough. This paper studies the effectiveness of symmetric rejection for multistage biometric verification systems. The symmetric rejection method determines the reject region by symmetrically rejecting equal proportion of genuine and impostor scores. The applicability of a multistage biometric verification system depends on how secure and user convenient it is, which is measured by the performance–cost trade-off. This paper analyzes the performance–cost trade-off of symmetric rejection method by conducting extensive experiments. Experiments are performed on two biometric databases: (1) publicly available NIST database and (2) a keystroke database. In addition, the symmetric rejection method is empirically compared with two existing rejection methods: (1) sequential probability ratio test-based method, which uses score-fusion and (2) Marcialis et al.’s method, which does not use score fusion. Results demonstrate strong effect of symmetric rejection method on creating a secure and user convenient multistage biometric verification system.

Teaching writing strategies based on writing processes has attracted wide attention as a method for developing writing skills. The writing process can be generally defined as a sequence of subtasks, such as planning, formulation, and revision. Therefore, instructor feedback is often given based on sequence patterns of those subtasks. For such feedback, instructors need to analyze sequence patterns for all learners, which becomes problematic as the number of learners increases. To resolve this problem, this study proposes a new machine-learning method that estimates sequence patterns from keystroke log data. Specifically, we propose an extension of the Gaussian hidden Markov model that incorporates parameters representing temporal change in a subtask appearance distribution for each learner. Furthermore, we propose a collapsed Gibbs sampling algorithm as the parameter estimation method for the proposed model. We demonstrate effectiveness of the proposed model by applying it to actual keystroke log datasets.

Keystroke data collected from smart devices includes various sensitive information about users. Collecting and analyzing such data raise serious privacy concerns. Google and Apple have recently applied local differential privacy (LDP) to address privacy issue on learning new words from users’ keystroke data. However, these solutions require multiple LDP reports for a single word, which result in inefficient use of privacy budget and high computational cost. In this paper, we develop a novel algorithm for learning new words under LDP. Unlike the existing solutions, the proposed method generates only one LDP report for a single word. This enables the proposed method to use full privacy budget for generating a report and brings the benefit that the proposed method provides better utility at the same privacy degree than the existing methods. In our algorithm, each user appends a hash value to new word and sends only one LDP report of an $n$ n -gram selected randomly from the string packed by each new word and its hash value. The server then decodes frequent $n$ n -grams at each position of the string and discovers the candidate words by exploring graph-theoretic links between $n$ n -grams and checking integrity of candidates with hash values. Frequencies of frequent new words discovered are estimated from distribution estimates of $n$ n -grams by robust regression. We theoretically show that our algorithm can recover popular new words even though the server does not know the domain of the raw data. In addition, we theoretically and empirically demonstrate that our algorithm achieves higher accuracy compared to the existing solutions.

Research in Keystroke-Dynamics (KD) has customarily focused on temporal features without considering context to generate user templates that are used in authentication. Additionally, work on KD in hand-held devices such as smart-phones and tablets have shown that these features alone do not perform satisfactorily for authentication. In this work, we analyze the discriminatory power of the most-used conventional features found in the literature, propose a set of context-sensitive or word-specific features, and analyze the discriminatory power of proposed features using their classification results. To perform these tasks, we use the keystroke data consisting of over 650K keystrokes, collected from 20 unique users during different activities on desktops, tablets, and phones, over a span of two months. On an average, each user made 12.5K, 9K, and 10K keystrokes on desktop, tablet, and phone, respectively. We find that the conventional features are not highly discriminatory on desktops and are only marginally better on hand-held devices for user identification. By using information of the context, a subset (derived after analysis) of our proposed word-specific features offers superior discrimination among users on all devices. We find that a majority of the classifiers, built using these features, perform user identification well with accuracies in the range of 90% to 97%, average precision and recall values of 0.914 and 0.901, respectively, on balanced test samples in 10-fold cross validation. We also find that proposed features work best on hand-held devices. This work calls for a shift from using conventional KD features to a set of context-sensitive or word-specific KD features that take advantage of known information such as context.

Keystroke behaviour-based authentication employs the unique typing behaviour of users to authenticate them. Recent such proposals for virtual keyboards on smartphones employ diverse temporal, contact, and spatial features to achieve over 95% accuracy. Consequently, they have been suggested as a second line of defense with text-based password authentication. We show that a state-of-the-art keystroke behaviour-based authentication scheme is highly vulnerable against mimicry attacks. While previous research used training interfaces to attack physical keyboards, we show that this approach has limited effectiveness against virtual keyboards. This is mainly due to the large number of diverse features that the attacker needs to mimic for virtual keyboards. We address this challenge by developing an augmented reality-based app that resides on the attacker’s smartphone and leverages computer vision and keystroke data to provide real-time guidance during password entry on the victim’s phone. In addition, we propose an audiovisual attack in which the attacker overlays transparent film printed with spatial pointers on the victim’s device and uses audio cues to match the temporal behaviour of the victim. Both attacks require neither tampering or installing software on the victim’s device nor specialized hardware. We conduct experiments with 30 users to mount over 400 mimicry attacks. We show that our methods enable an attacker to mimic keystroke behaviour on virtual keyboards with little effort. We also demonstrate the extensibility of our augmented reality-based technique by successfully mounting mimicry attacks on a swiping behaviour-based continuous authentication system.

Cyber attackers are always seeking to design and push malicious software programs to unsuspecting users, to intentionally steal or cause damage and exploit data on end user systems. Malware types include spyware, keyloggers, rootkits and adware. In the past, script kiddies hacked computers to show off their skills and have fun. Today, hacking computers has become a huge cybercrime industry. Even as systems have improved in terms of both hardware and software, cyber attacks continue unabated. The privilege level at which keyloggers execute is higher than typical malware, which makes them almost impossible to detect and remove. Dr Akashdeep Bhardwaj of the University of Petroleum & Energy Studies, Dehradun, and Dr Sam Goundar of the University of South Pacific, demonstrate how a keylogger can gather keystrokes and screenshots along with online transactions without a scanner being able to detect it. They also suggest a form of virtual keyboard that could defeat this kind of malware.

In this study, we present WindTalker, a novel and practical keystroke inference framework that can be used to infer the sensitive keystrokes on a mobile device through WiFi-based side-channel information. WindTalker is motivated from an observation that keystrokes on mobile devices will lead to different hand coverage and the finger motions, which will introduce a unique interference to the multi-path signals and can be reflected by the channel state information (CSI). An attacker can exploit the strong correlation between the CSI fluctuation and the keystrokes to infer the user's password input. Compared with the previous keystroke inference approaches, WindTalker neither deploys external equipment physically close to the target device nor compromises the target device. Instead, it employs a more practical setting by deploying a free public WiFi hotspot and collects the CSI data from the target device as long as the device is connected to the hotspot. In addition, to improve inference accuracy and efficiency, it analyzes the WiFi traffic to selectively collect CSI only for the sensitive period where password entering occurs. WindTalker can be implemented without the requirement of visually seeing the target device, or installing any malware on the device. We tested Windtalker on several mobile phones and performed a detailed case study to evaluate the practicality of the password inference towards Alipay, the largest mobile payment platform in the world. Furthermore, we proposed a novel CSI obfuscation countermeasure to thwart the inference attack. The evaluation results show that the performance of WindTalker can be dramatically reduced by adopting the proposed countermeasures.

Over the past decade, keystroke-based pattern recognition techniques, as a forensic tool for behavioral biometrics, have gained increasing attention. Although a num- ber of machine learning-based approaches have been proposed, they are limited in terms of their capability to recognize and profile a set of an individual’s characteristics. In addition, up to today, their focus was primarily gender and age, which seem to be more appropriate for commercial applications (such as developing commercial software), leaving out from research other characteristics, such as the educational level. Educational level is an acquired user characteristic, which can improve targeted advertising, as well as provide valuable information in a digital forensic investigation, when it is known. In this context, this paper proposes a novel machine learning model, the randomized radial basis function network, which recognizes and profiles the edu- cational level of an individual who stands behind the keyboard. The performance of the proposed model is evaluated by using the empirical data obtained by recording volunteers’ keystrokes during their daily usage of a computer. Its performance is also compared with other well-referenced machine learning models using our keystroke dynamic datasets. Although the proposed model achieves high accuracy in educational level prediction of an unknown user, it suffers from high computational cost. For this reason, we examine ways to reduce the time that is needed to build our model, including the use of a novel data condensation method, and discuss the tradeoff between an accurate and a fast prediction. To the best of our knowledge, this is the first model in the literature that predicts the educational level of an individual based on the keystroke dynamics information only.

In our previous work, we developed an IMU (Inertial Measurement Unit) based smart ring that allows users to type characters without a physical keyboard and adopt well-known pattern recognition algorithms, such as Support Vector Machine (SVM), and Naive Bayes (NB), for keystroke recognition. However, these algorithms always require intensive computing resources or offer limited recognition accuracy. Moreover, they are often seen as black boxes incapable of providing readily comprehensible and visible clues for classification. This hampers the improvement of keystroke recognition accuracy and the ring-type virtual keyboard’s character layout design. Here we present a novel algorithm to recognize keystrokes in a fast and accurate manner. Firstly, the standard feature vector, including five attitude angle features and one acceleration feature, is built to express a specific stroke. Then, the feature vector of the testing keystroke is compared with the standard features. The most similar keystroke is matched and recognized after three times of voting. Based on this algorithm, we can identify the easily confused keystrokes and understand the mechanisms behind it. With this interpretability, we will be able to achieve the customized ring-type virtual keyboard application if necessary. The performance of this algorithm was evaluated by using a dataset with 1500 keystrokes of three different subjects. The results show that our algorithm is more effective in keystroke recognition than traditional algorithms for this ring-type keyboard. In addition to its application on virtual keyboards, this algorithm can also be potentially applied on other classification tasks with easy-to-understand results.

Two-factor authentication (2FA) systems implement by verifying at least two factors. A factor can be one or more of something a user knows (password, or phrase), something a user possesses (smart card, or smartphone), something a user is (fingerprint, or iris), something a user does (keystroke), or somewhere a user is (location). In a conventional 2FA system, a user is required to interacts (e.g., typing a passcode) in order to implement the second layer of authentication, which is not very user-friendly. Nowadays, smart devices (phones, laptops, tablets, etc.) can receive signals from different radio frequency technologies within range. As these devices move among networks (Wi-Fi access points, cell phone towers, etc.), they receive broadcast messages, some of which can be used to collect information. This information can be utilized in a variety of ways, such as establishing a connection, sharing information, locating devices, and, most appropriately, identifying users in range. The principal benefit of broadcast messages is that the devices can read and process the embedded information without being connected to the broadcaster. Moreover, the broadcast messages can be received only within a range of the wireless access point sending the broadcast, thus inherently limiting access to those devices in close physical proximity and facilitating many applications dependent on that proximity. In this paper, 0EISUA is proposed, a zero-effort two-factor authentication scheme based on something that is in the user's environment (ambient access points). In our research, data from the broadcast messages are utilized to implement the second authentication factor by determining whether two devices are proximate or not to ensure that they belong to the same user, in a way that requires zero interaction from the user. The new proposed system introduced in this paper is experimentally tested.

This paper investigates some specific features of continuous user identification based on hidden monitoring of keystroke dynamics when creating a free text. Our analysis of static identification approaches does not reveal any significant limitations on their application to continuous identification. The main feature of continuous identification is the method for collecting dynamic information about key presses and the correction of templates of registered users. The effectiveness of including additional classification features in recognition algorithms, e.g., those associated with the frequency of letters in texts, is demonstrated. A software application is developed to collect and analyze keystroke rhythm samples of users. Research in the domain of users with good computer skills shows quite satisfactory user recognition accuracy (87% on average). Moreover, the accuracy does not depend on the metric distance selected for recognition and improves with the use of scaling factors for letter frequency.

Learning dashboards are often used to provide teachers with insight into students’ learning processes. However, simply providing teachers with data on students’ learning processes is not necessarily beneficial for improving learning and teaching; the data need to be actionable. Recently, human-centered learning analytics has been suggested as a solution to realize more effective and actionable dashboards. Accordingly, this study aims to identify how these human-centered approaches could be used to design an interpretable and actionable learning dashboard on students’ writing processes. The design consists of three iterative steps. First, visualizations on students’ revision process, created from keystroke data, were evaluated with writing researchers. Second, the updated visualizations were used to co-design a paper prototype of the dashboard within a focus group session with writing teachers. Finally, the paper prototype was transformed into a digital prototype and evaluated by teachers in individual user test interviews. The results showed that this approach was useful for designing an interpretable dashboard with envisioned actions, which could be further tested in classroom settings.

Current writing support tools tend to focus on assessing final or intermediate products, rather than the writing process. However, sensing technologies, such as keystroke logging, can enable provision of automated feedback during, and on aspects of, the writing process. Despite this potential, little is known about the critical indicators that can be used to effectively provide this feedback. This article proposes a participatory approach to identify the indicators of students’ writing processes that are meaningful for educational stakeholders and that can be considered in the design of future systems to provide automated, personalized feedback. This approach is illustrated through a qualitative research design that included five participatory sessions with five distinct groups of stakeholders: bachelor and postgraduate students, teachers, writing specialists, and professional development staff. Results illustrate the value of the proposed approach, showing that students were especially interested in lower-level behavioral indicators, while the other stakeholders focused on higher-order cognitive and pedagogical constructs. These findings lay the groundwork for future work in extracting these higherlevel indicators from in-depth analysis of writing processes. In addition, differences in terminology and the levels at which the indicators were discussed, highlight the need for human-centered, participatory approaches to design and develop writing analytics tools.

This study presents Periscope, a novel side-channel attack that exploits human-coupled electromagnetic (EM) emanations from touchscreens to infer sensitive inputs on a mobile device. Periscope is motivated by the observation that finger movement over the touchscreen leads to time-varying coupling between these two. Consequently, it impacts the screen's EM emanations that can be picked up by a remote sensory device. We intend to map between EM measurements and finger movements to recover the inputs. As the significant technical contribution of this work, we build an analytic model that outputs finger movement trajectories based on given EM readings. Our approach does not need a large amount of labeled dataset for offline model training, but instead a couple of samples to parameterize the user-specific analytic model. We implement Periscope with simple electronic components and conduct a suite of experiments to validate this attack's impact. Experimental results show that Periscope achieves a recovery rate over 6-digit PINs of 56.2% from a distance of 90 cm. Periscope is robust against environment dynamics and can well adapt to different device models and setting contexts.

Recently, smart devices equipped with microphones have become increasingly popular in people's lives. However, when users type on a keyboard near devices with microphones, the acoustic signals generated by different keystrokes may leak the user's privacy. This paper proposes a robust side-channel attack scheme to infer keystrokes on the surrounding keyboard, leveraging the smart devices' microphones. To address the challenge of non-cooperative attacking environments, we propose an efficient scheme to estimate the relative position between the microphones and the keyboard, and extract two robust features from the acoustic signals to alleviate the impact of various victims and keyboards. As a result, we can realize the side-channel attack through acoustic signals, regardless of the exact location of microphones, the victims, and the type of keyboards. We implement the proposed scheme on the commercial smartphone and conduct extensive experiments to evaluate its performance. Experimental results show that the proposed scheme could achieve good performance in predicting keyboard input under various conditions. Overall, we can correctly identify 91.2% of keystrokes with 10-fold cross-validation. When predicting keystrokes from unknown victims, the attack can obtain a Top-5 accuracy of 91.52%. Furthermore, the Top-5 accuracy of predicting keystrokes can reach 72.25% when the victims and keyboards are both unknown. When predicting meaningful contents, we can obtain a Top-5 accuracy of 96.67% for the words entered by the victim.

Nowadays, many companies use biometric technologies for the security of critical systems as well as username-password methods. In the literature, biometric systems are the most commonly used systems among the two-factor authentication systems. There are two different approaches to biometric systems: physical and behavioral biometric systems. In the last decade, the accuracy of behavioral biometric systems has significantly increased with the use of machine learning methods in these systems. For this reason, the usage areas of the studies in this field have expanded. In this study, we focus on keystroke dynamics based on behavioral methods. Firstly, we make a web application to collect keystroke data from 54 employees in a company. Then, we use the benchmark database and our database to train-test machine learning algorithms, which have the highest accuracy in this field in the literature. Among them, tree-based algorithms have the highest accuracy score, with an average of 0.94.

Android is presently the world’s most prevalent operating system, reaching more mobile customers than any other operating system to date by providing numerous services via smartphone and various android devices to make our life easy. Most of the android applications are developed by third-party android developers, android provides them an enormous platform to build their application. Modern cyber attackers are highly interested in this platform to access user’s sensitive information; with their own build malicious application or take amenities of other android developer’s application to spy on user’s activity. We have found that keyloggers can thieve personal information from users, such as credit card information or login pin/password from their typed keystroke in social networking and mobile banking apps. In case of mobile banking generally the mobile devices such as smartphones, tablets are being used for financial communications with the banks or financial institutions, by allowing clients and users to conduct a variety of transactions. In android app store (Google Play) keylogger apps are initially blocked but using some vulnerabilities in app permission it can be installed with benign and trusted apps. Both expert and maladroit android smartphone users use the mobile banking application, inexpert users are unable to find the vulnerabilities and attacker’s use this as an advantage to place an attack. The security android has provided for all the application is not sufficient for the sensitive application such as mobile banking application. In our paper, we discuss how attackers steal mobile banking app users sensitive information for their financial gain and also proposed a method to avoid keylogger attacks on android mobile banking apps.

The human state of mind can be reflected in interactions with computers, such as the time taken to type a word, the number of times that a correction is made, the average time taken to press a set of keys, etc. In this research, we developed an application that captures keystroke-based human-computer interactions while gathering user mood (pleasant vs. unpleasant) information utilizing a pre-established survey instrument – the Brief Mood Introspection Survey (BMIS). Using keystroke-based features and saliency measurements of the features, we constructed models to differentiate between pleasant and unpleasant moods. Once unpleasant moods are detected, possible interventions can be applied. For unpleasant mood detection, generalized neural network (GRNN), probabilistic neural network (PNN), and Levenberg-Marquardt neural network (LMNN) algorithms provided the best F1-scores, whereas decision tree (DT) algorithm provided the best recall score.

Universal Serial Bus (USB) devices are a standard method for information exchange. The growth in the usage of USB devices has increased the risk of vulnerabilities through which an adversary can exploit connected systems. Mostly, attackers tend to hamper the firmware of USB devices and try to inject malicious scripts into the system through keypresses, causing a keypress injection attack. This paper aims to develop a framework based on free-text keystroke dynamics for detecting keypress injection attacks. The mechanism uses various machine learning models trained over different keystroke features such as duration time features (Hold Time) and latency features (Up-Down Time and Down-Down Time). We implement a realtime continuous checking over the latency features of user keystrokes. The trained models subsequently predict whether the user activity lies in the genuine or malicious region. We have used different baseline classifiers including k-Nearest Neighbour(KNN), Support Vector Machine(SVM), Random Forest, XGBoost, and investigated three custom-made keypress injection attacks in each model. The results indicate that Random Forest provides the best detection accuracy over all the three applied attacks. Furthermore, we compared the models trained with our dataset to those trained with the Buffalo dataset. Interestingly, our trained models demonstrate comparable accuracy with the former one, thereby vindicating the utility of the dataset.

Program writing is difficult to teach, learn, and assess. One challenge is a lack of theory or understanding about what program writing is. My dissertation will address this challenge by applying theories from natural language (NL) writing to try and understand program writing as a cognitive process. By analyzing keystroke logs collected during program writing, I plan to identify similarities with NL writing, potential diagnostic information, and how program writing changes as students become more proficient.