Search

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

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.

Cyberattack is one of the severe threats in the digital world as it encompasses everything related to personal information, health, finances, intellectual properties, and even national security. Password‐based authentication is the most practiced authentication system, however, is vulnerable to several attacks such as dictionary attack, shoulder surfing attack, and guessing attack. Here, a new keystroke dynamics‐based hybrid nanogenerator for biometric authentication and identification integrated with artificial intelligence (AI) is reported. Keystroke dynamics offer behavioral and contextual information that can distinguish and authorize the individuals based on their typing rhythms. The hybrid electromagnetic‐triboelectric nanogenerators/sensors efficiently convert the keystroke mechanical energy into electrical signals, which are fed into an artificial neural network based AI system. The self‐powered hybrid sensors‐based biometric authentication system integrated with a neural network achieves an accuracy of 99% and offers a promising hybrid security layer against password vulnerability., Cybersecurity is one of the severe issues in this modern computing world where password‐based security is being more vulnerable. Herein, a keystroke dynamics‐based hybrid electromagnetic‐triboelectric nanogenerator for biometric authentication and identification system integrated with artificial intelligence is developed with an excellent accuracy of 99%.

This study investigated whether task complexity influences second language (L2) writers’ fluency, pausing, and revision behaviors and the cognitive processes underlying these behaviors; whether task complexity affects linguistic complexity of written output; and whether relationships between writing behaviors and linguistic complexity are moderated by task complexity. Participants were 73 advanced L2 writers, who completed simple or complex essay tasks. Task complexity was operationalized as the absence versus presence of content support. Participants’ writing behaviors were recorded via keystroke logging software. Four writers, drawn from groups performing simple and complex tasks, additionally engaged in stimulated recall. Content support was found to lead to less pausing, more revision, and increased linguistic complexity. When content support was absent, more frequent pauses and revisions were associated with less sophisticated lexis. These results, combined with stimulated recall comments, suggest that content support likely reduced processing burden on planning processes, facilitating attention to linguistic encoding.

User authentication is a crucial requirement for cloud service providers to prove that the outsourced data and services are safe from imposters. Keystroke dynamics is a promising behavioral biometrics for strengthening user authentication, however, current keystroke based solutions designed for certain datasets, for example, a fixed length text typed on a traditional personal computer keyboard and their authentication performances were not acceptable for other input devices nor free length text. Moreover, they suffer from a high dimensional feature space that degrades the authentication accuracy and performance.

In educational measurement contexts, essays have been evaluated and formative feedback has been given based on the end product. In this study, we used a large sample collected from middle school students in the United States to investigate the factor structure of the writing process features gathered from keystroke logs and the association of that latent structure with the quality of the final product (i.e., the essay text). The extent to which those process factors had incremental value over product features was also examined. We extracted 29 process features using the keystroke logging engine developed at Educational Testing Service (ETS). We identified 4 factors that represent the extent of writing fluency, local word-level editing, phrasal/chunk-level editing, and planning and deliberation during writing. We found that 2 of the 4 factors—writing fluency, and planning and deliberation—significantly related to the quality of the final text, whereas the 4 factors altogether accounted for limited variance in human scores. In 1 of the 2 samples studied, the keystroke-logging fluency factor added incrementally, but only marginally, to the prediction of human ratings of text-production skills beyond product features. The limited power of the writing process features for predicting human scores and the lack of clear additional predictive value over product features are not surprising given that the human raters have no knowledge of the writing process leading to the final text and that the product features measure the basic text quality specified in the human scoring rubric. Study limitations and recommendation for future research are also provided.

In this report, we examine the feasibility of characterizing writing performance using process features derived from a keystroke log. Using data derived from a set of CBAL™ writing assessments, we examine the following research questions: (a) How stable are the keystroke timing and process features across testing occasions? (b) How consistent are the patterns of feature–human correlation across genres and topics? (c) How accurately can we predict human ratings on writing fundamentals using a combination of the keystroke timing and process features, and what are the contributions of each feature to the reliable variance in the human ratings? (d) If we train a predictive model on one prompt, how well do its predictions generalize to the other prompts of the same or different genre? The results of the study indicate that keystroke log features vary considerably in stability across testing occasions and display somewhat different patterns of feature–human correlation across genres and topics. However, using the most stable features, we can obtain moderate to strong prediction of human essay scores, and those models generalize reasonably well across prompts though more strongly within than across writing genres.

Keystroke dynamics is a well-investigated behavioural biometric based on the way and rhythm in which someone interacts with a keyboard or keypad when typing characters. This paper explores the potential of this modality but for touchscreen-equipped smartphones. The main research question posed is whether 'touchstroking' can be effective in building the biometric profile of a user, in terms of typing pattern, for future authentication. To reach this goal, we implemented a touchstroke system in the Android platform and executed different scenarios under disparate methodologies to estimate its effectiveness in authenticating the end-user. Apart from typical classification features used in legacy keystroke systems, we introduce two novel ones, namely, speed and distance. From the experiments, it can be argued that touchstroke dynamics can be quite competitive, at least when compared to similar results obtained from keystroke evaluation studies. As far as we are aware of, this is the first time this newly arisen behavioural trait is put into focus. Copyright © 2014 John Wiley & Sons, Ltd.

After verifying the correctness of the password, the keystroke dynamics-based authentication KDA system will verify the corresponding keystroke features. It provides additional security verification for alphanumeric-based and personal identification number-based authentication schemes that suffer from guessing and shoulder surfing attacks. Except for the original time features in the KDA schemes, two novel keystroke features are found in touch screen handheld mobile devices, which are called "pressure" features and "size" features. A computation efficient statistical classifier is built for low-power mobile devices to authenticate the user's identity. This paper analyzes the following combinations of features: 1 time features; 2 time features and pressure features; 3 time features and size features; and 4 all features combined. The result shows that the size features or the pressure features can effectively promote the utility of the KDA system in personal identification number-based authentication schemes for touch screen handled mobile devices. The combination of time features and pressure features is the best one for authenticating users. Copyright © 2013 John Wiley & Sons, Ltd.

Data comparability between different laboratories strongly depends on the individually applied analysis method. This factor is often a critical source of variation in rodent phenotyping and has never been systematically investigated in Pavlovian fear conditioning paradigms. In rodents, fear is typically quantified in terms of freezing duration via manual observation or automated systems. While manual analysis includes biases such as tiredness or inter-personal scoring variability, computer-assisted systems are unable to distinguish between freezing and immobility. Consequently, the novel software called MOVE follows a semi-automatized approach that prefilters video sequences of interest for the final human judgment. Furthermore, MOVE allows integrating additional data sources (e.g. force-sensitive platform, EEG) to reach the most accurate and precise results. MOVE directly supports multi-angle video recordings with webcams or standard laboratory equipment. The integrated manual key logger and internal video player complement this all-in-one software solution. Calculating the interlaboratory variability of manual freezing evaluation revealed significantly different freezing scores in two out of six laboratories. This difference was minimized when all experiments were analyzed with MOVE. Applied to a genetically modified mouse model, MOVE revealed higher fear responses of CB1 deficient mice compared to their wild-type littermates after foreground context fear conditioning. Multi-angle video analysis compared to the single-camera approach reached up to 15% higher accuracy and two fold higher precision. Multidimensional analysis provided by integration of additional data sources further improved the overall result. We conclude that the widespread usage of MOVE could substantially improve the comparability of results from different laboratories.

The psycholinguistic dimension in second language writing: Opportunities for research and pedagogy using computer keystroke logging

This teaching brief presents a Microsoft® Excel simulation designed to complement and expand upon the well-known matchstick/die game introduced by Goldratt in The Goal. This simulation performs 100 replications of a 40-period processing run for low, medium, and high levels of process variation and displays the comparative results graphically. A single keystroke repeats the process and updates the displays so that the stability of the essential conclusions in the face variation is illustrated dynamically. Suggestions for using the simulation in class are included.

Hierarchical goal decompositions have proved to be a useful method to make explicit the knowledge required by users to perform tasks in a wide range of applications such as computer-aided drafting (CAD) systems. This analysis method progressively decomposes a given task starting from the task layer on the top of the decomposition, to the keystroke layer at the bottom. The analysis enables a close inspection of the knowledge required to perform the task at each layer of the decomposition. In this paper we show how the method of hierarchical goal decomposition can be used to understand more precisely the knowledge that is required to perform information search tasks. The analysis pinpoints: (1) the critical strategies in the intermediate layers of knowledge that are known by experts searchers; (2) why such knowledge is difficult to acquire by novice searchers; (3) how the analysis provides testable predictions of behavior based on the acquisition of different types of knowledge. We conclude by discussing the advantages provided by hierarchical goal decompositions, and how such an approach can lead to the design of systems and training.

How do children solve force and motion problems in computer simulations without explicit knowledge of the underlying physics? This question was addressed by saving the keystroke input of 19 sixth-grade children in computer memory as each interacted with a simulated, frictionless object using Logo turtle-graphics. The keystroke sequences were first used to determine subject performance on the gamelike features of the simulation. A second analysis used the Newtonian structure of the program to investigate alternative methods for controlling turtle velocity. Five boys and five girls were interviewed during the simulation concerning the perceived relationship between keyboard input and turtle behavior. Subjects who could clearly state some keyboard effects did not score high on either computer analysis, yet achieved the most general solutions of the computer problem. They did so by exploring turtle behavior under a greater variety of conditions than the subjects who achieved partial solutions. For the successful subjects, the turtle was related by analogy to useful information from existing conceptions of motion.

A power-law model for simulating advancement of typing speed is discussed in this article. Through a long-term training experiment of a coded typing for inputting Japanese, some new properties have been found through the analysis of the training records of many subjects. The major one is that every practice time to complete each drill, which is a segment of practice, statistically satisfies a power law. A few versions of the model succeed in simulating this phenomenon, if they assume that advancement of strokes for every character satisfies a power law. However, they fail in detailing the initial records. An extended version further including a power-law advancement of recalling codes and a temporary memory holding a few codes succeeds in detailing them only when the temporary memory size is 2. This number agrees with the well-known one, or the number of chunks to be held in the short-term memory, unless one character code requires four chunks as a pair of two coordinates on a keyboard. Some keystroke timing data supporting the model are observed in another training system.

The Fall 2007 and Spring 2008 pilot tests for the CBAL™ Writing assessment included experimental keystroke logging capabilities. This report documents the approaches used to capture the keystroke logs and the algorithms used to process the outputs. It also includes some preliminary findings based on the pilot data. In particular, it notes that the distribution of most of the pause length is consistent with data generated from a mixture of lognormal distributions. This corresponds to a cognitive model in which some pauses are merely part of the transcription (i.e., typing) process and some are part of more involved cognitive process (e.g., attention to writing conventions, word choice, and planning). In the pilot data, many of the features extracted from the keystroke logs were correlated with human scores. Due to the small sample sizes of the pilot studies, these findings are suggestive, not conclusive; however, they suggest a line of analysis for a large sample containing keystroke logging gathered in the fall of 2009.