Biblio

Next Word Prediction involves guessing the next word which is most likely to come after the current word. The system suggests a few words. A user can choose a word according to their choice from a list of suggested word by system. It increases typing speed and reduces keystrokes of the user. It is also useful for disabled people to enter text slowly and for those who are not good with spellings. Previous studies focused on prediction of the next word in different languages. Some of them are Bangla, Assamese, Ukraine, Kurdish, English, and Hindi. According to Census 2011, 43.63% of the Indian population uses Hindi, the national language of India. In this work, deep learning techniques are proposed to predict the next word in Hindi language. The paper uses Long Short Term Memory and Bidirectional Long Short Term Memory as the base neural network architecture. The model proposed in this work outperformed the existing approaches and achieved the best accuracy among neural network based approaches on IITB English-Hindi parallel corpus.

The recent experience in the use of virtual reality (VR) technology has shown that users prefer Electromyography (EMG) sensor-based controllers over hand controllers. The results presented in this paper show the potential of EMG-based controllers, in particular the Myo armband, to identify a computer system user. In the first scenario, we train various classifiers with 25 keyboard typing movements for training and test with 75. The results with a 1-dimensional convolutional neural network indicate that we are able to identify the user with an accuracy of 93% by analyzing only the EMG data from the Myo armband. When we use 75 moves for training, accuracy increases to 96.45% after cross-validation.

Smart Phones being a revolution in this Modern era which is considered a boon as well as a curse, it is a known fact that most kids of the current generation are addictive to smartphones. The National Institute of Health (NIH) has carried out different studies such as exposure of smartphones to children under 12 years old, health risk associated with their usage, social implications, etc. One such study reveals that children who spend more than two hours a day, on smartphones have been seen performing poorly when it comes to language and cognitive skills. In addition, children who spend more than seven hours per day were diagnosed to have a thinner brain cortex. Hence, it is of great importance to control the amount of exposure of children to smartphones, as well as access to irregulated content. Significant research work has gone in this regard with a plethora of inputs features, feature extraction techniques, and machine learning models. This paper is a survey of the State-of-the-art techniques in detecting the age of the user using machine learning models on touch, keystroke dynamics, and sensor data.

Pauses in typing are generally considered to indicate cognitive processing and so are of interest in educational contexts. While much prior work has looked at typing behavior of Computer Science students, this paper presents results of a study specifically on the pausing behavior of students in Introductory Computer Programming. We investigate the frequency of pauses of different lengths, what last actions students take before pausing, and whether there is a correlation between pause length and performance in the course. We find evidence that frequency of pauses of all lengths is negatively correlated with performance, and that, while some keystrokes initiate pauses consistently across pause lengths, other keystrokes more commonly initiate short or long pauses. Clustering analysis discovers two groups of students, one that takes relatively fewer mid-to-long pauses and performs better on exams than the other.

User authentication based on muscle tension manifested during password typing seems to be an interesting additional layer of security. It represents another way of verifying a person’s identity, for example in the context of continuous verification. In order to explore the possibilities of such authentication method, it was necessary to create a capturing software that records and stores data from EMG (electromyography) sensors, enabling a subsequent analysis of the recorded data to verify the relevance of the method. The work presented here is devoted to the design, implementation and evaluation of such a solution. The solution consists of a protocol and a software application for collecting multimodal data when typing on a keyboard. Myo armbands on both forearms are used to capture EMG and inertial data while additional modalities are collected from a keyboard and a camera. The user experience evaluation of the solution is presented, too.

The impact of digital gadgets is enormous in the current Internet world because of the easy accessibility, flexibility and time-saving benefits for the consumers. The number of computer users is increasing every year. Meanwhile, the time spent and the computers also increased. Computer users browse the internet for various information gathering and stay on the internet for a long time without control. Nowadays working people from home also spend time with the smart devices, computers, and laptops, for a longer duration to complete professional work, personal work etc. the proposed study focused on deriving the impact factors of Smartphones by analyzing the keystroke dynamics Based on the usage pattern of keystrokes the system evaluates the stress level detection using machine learning techniques. In the proposed study keyboard users are intended for testing purposes. Volunteers of 200 members are collectively involved in generating the test dataset. They are allowed to sit for a certain frame of time to use the laptop in the meanwhile the keystroke of the Mouse and keyboard are recorded. The system reads the dataset and trains the model using the Dynamic Cat-Boost algorithm (DCB), which acts as the classification model. The evaluation metrics are framed by calculating Euclidean distance (ED), Manhattan Distance (MahD), Mahalanobis distance (MD) etc. Quantitative measures of DCB are framed through Accuracy, precision and F1Score.

This research studies the effect of a countdown timer and a count-up timer on the keystroke pattern of the student and finds out whether changing the timer type changes the keystroke pattern. It also points out which timer affects more students in a timer environment during exams. We used two hypothesis testing statistical Algorithms, namely, the Two-Sample T-Test and One-way ANOVA Test, for analysis to identify the effect of different times our whether significant differences were found in the keystroke pattern or not when different timers were used. The supporting results have been found with determines that timer change can change the keystroke pattern of the student and from the study of hypothesis testing, different students result from different types of stress when they are under different timer environments.

Many smartphones are lost every year, with a meager percentage recovered. In many cases, users with malicious intent access these phones and use them to acquire sensitive data. There is a need for continuous monitoring and surveillance in smartphones, and keystroke dynamics play an essential role in identifying whether a phone is being used by its owner or an impersonator. Also, there is a growing need to replace expensive 2-tier authentication methods like One-time passwords (OTP) with cheaper and more robust methods. The methods proposed in this paper are applied to existing data and are proven to train more robust classifiers. A novel feature extraction method by wavelet transformation is demonstrated to convert keystroke data into features. The comparative study of classifiers trained on the extracted features vs. features extracted by existing methods shows that the processes proposed perform better than the state-of-art feature extraction methods.

Keystroke dynamics is one solution to enhance the security of password authentication without adding any disruptive handling for users. Industries are looking for more security without impacting too much user experience. Considered as a friction-less solution, keystroke dynamics is a powerful solution to increase trust during user authentication without adding charge to the user. In this paper, we address the problem of user authentication considering the keystroke dynamics modality. We proposed a new approach based on the conversion of behavioral biometrics data (time series) into a 3D image. This transformation process keeps all the characteristics of the behavioral signal. The time series do not receive any filtering operation with this transformation and the method is bijective. This transformation allows us to train images based on convolutional neural networks. We evaluate the performance of the authentication system in terms of Equal Error Rate (EER) on a significant dataset and we show the efficiency of the proposed approach on a multi-instance system.

With the advent of technology and owing to mankind’s reliance on technology, it is of utmost importance to safeguard people’s data and their identity. Biometrics have for long played an important role in providing that layer of security ranging from small scale uses such as house locks to enterprises using them for confidentiality purposes. In this paper we will provide an insight into behavioral biometrics that rely on identifying and measuring human characteristics or behavior. We review different types of behavioral parameters such as keystroke dynamics, gait, footstep pressure signals and more.

The ever-growing security issues in various mobile applications and smart devices create an urgent demand for a reliable and convenient user verification method. Traditional verification methods request users to provide their secrets (e.g., entering passwords and collecting fingerprints). We envision that the essential trend of user verification is to free users from active participation in the verification process. Toward this end, we propose a continuous user verification system, which re-uses the widely deployed WiFi infrastructure to capture the unique physiological characteristics rooted in user's respiratory motions. Different from the existing continuous verification approaches, posing dependency on restricted scenarios/user behaviors (e.g., keystrokes and gaits), our system can be easily integrated into any WiFi infrastructure to provide non-intrusive continuous verification. Specifically, we extract the respiration-related signals from the channel state information (CSI) of WiFi. We then derive the user-specific respiratory features based on the waveform morphology analysis and fuzzy wavelet transformation of the respiration signals. Additionally, a deep learning based user verification scheme is developed to identify legitimate users accurately and detect the existence of spoofing attacks. Extensive experiments involving 20 participants demonstrate that the proposed system can robustly verify/identify users and detect spoofers under various types of attacks.

Increased peripheral performance is causing strain on the memory subsystem of modern processors. For example, available DRAM throughput can no longer sustain the traffic of a modern network card. Scrambling to deliver the promised performance, instead of transferring peripheral data to and from DRAM, modern Intel processors perform I/O operations directly on the Last Level Cache (LLC). While Direct Cache Access (DCA) instead of Direct Memory Access (DMA) is a sensible performance optimization, it is unfortunately implemented without care for security, as the LLC is now shared between the CPU and all the attached devices, including the network card.In this paper, we reverse engineer the behavior of DCA, widely referred to as Data-Direct I/O (DDIO), on recent Intel processors and present its first security analysis. Based on our analysis, we present NetCAT, the first Network-based PRIME+PROBE Cache Attack on the processor's LLC of a remote machine. We show that NetCAT not only enables attacks in cooperative settings where an attacker can build a covert channel between a network client and a sandboxed server process (without network), but more worryingly, in general adversarial settings. In such settings, NetCAT can enable disclosure of network timing-based sensitive information. As an example, we show a keystroke timing attack on a victim SSH connection belonging to another client on the target server. Our results should caution processor vendors against unsupervised sharing of (additional) microarchitectural components with peripherals exposed to malicious input.

Side-channel attacks occur on smartphone keystrokes, where the input can be intercepted by a tapping sound. Ilia et al. reported that keystrokes can be predicted with 61% accuracy from tapping sounds listened to by the built-in microphone of a legitimate user's device. Li et al. reported that by emitting sonar sounds from an attacker smartphone's built-in speaker and analyzing the reflected waves from a legitimate user's finger at the time of tap input, keystrokes can be estimated with 90% accuracy. However, the method proposed by Ilia et al. requires prior penetration of the target smartphone and the attack scenario lacks plausibility; if the attacker's smartphone can be penetrated, the keylogger can directly acquire the keystrokes of a legitimate user. In addition, the method proposed by Li et al. is a side-channel attack in which the attacker actively interferes with the terminals of legitimate users and can be described as an active attack scenario. Herein, we analyze the extent to which a user's keystrokes are leaked to the attacker in a passive attack scenario, where the attacker wiretaps the sounds of the legitimate user's keystrokes using an external microphone. First, we limited the keystrokes to the personal identification number input. Subsequently, mel-frequency cepstrum coefficients of tapping sound data were represented as image data. Consequently, we found that the input is discriminated with high accuracy using a convolutional neural network to estimate the key input.

The following topics are dealt with: authorisation; data privacy; mobile computing; security of data; cryptography; Internet of Things; message authentication; invasive software; Android (operating system); vectors.

Keystroke Inference has been a hot topic since it poses a severe threat to our privacy from typing. Existing learning-based Keystroke Inference suffers the domain adaptation problem because the training data (from attacker) and the test data (from victim) are generally collected in different environments. Recently, Optimal Transport (OT) is applied to address this problem, but suffers the “ground metric” limitation. In this work, we propose a novel method, OTDA, by incorporating Discriminant Analysis into OT through an iterative learning process to address the ground metric limitation. By embedding OTDA into a vibration-based Keystroke Inference platform, we conduct extensive studies about domain adaptation with different factors, such as people, keyboard position, etc.. Our experiment results show that OTDA can achieve significant performance improvement on classification accuracy, i.e., outperforming baseline by 15% to 30%, state-of-the-art OT and other domain adaptation methods by 10% to 20%.

Expressing Keystroke Dynamics (KD) in form of sound opens new avenues to apply sound analysis techniques on KD. However this mapping is not straight-forward as varied feature space, differences in magnitudes of features and human interpretability of the music bring in complexities. We present a musical interface to KD by mapping keystroke features to music features. Music elements like melody, harmony, rhythm, pitch and tempo are varied with respect to the magnitude of their corresponding keystroke features. A pitch embedding technique makes the music discernible among users. Using the data from 30 users, who typed fixed strings multiple times on a desktop, shows that these auditory signals are distinguishable between users by both standard classifiers (SVM, Random Forests and Naive Bayes) and humans alike.

Nowadays, smartphones are everywhere. They play an indispensable role in our lives and makes people convenient to communicate, pay, socialize, etc. However, they also bring a lot of security and privacy risks. Keystroke operations of numeric keypad are often required when users input password to perform mobile payment or input other privacy-sensitive information. Different keystrokes may cause different finger movements that will bring different interference to WiFi signal, which may be reflected by channel state information (CSI). In this paper, we propose WiPass, a password-keystroke recognition system for numerical keypad input on smartphones, which especially occurs frequently in mobile payment APPs. Based on only a public WiFi hotspot deployed in the victim payment scenario, WiPass would extracts and analyzes the CSI data generated by the password-keystroke operation of the smartphone user, and infers the user's payment password by comparing the CSI waveforms of different keystrokes. We implemented the WiPass system by using COTS WiFi AP devices and smartphones. The average keystroke segmentation accuracy was 80.45%, and the average keystroke recognition accuracy was 74.24%.

In the present scenario, security is the biggest concern in any domain of applications. The latest and widely used system for user authentication is a biometric system. This includes fingerprint recognition, retina recognition, and voice recognition. But these systems can be bypassed by masqueraders. To avoid this, a combination of these systems is used which becomes very costly. To overcome these two drawbacks keystroke dynamics were introduced in this field. Keystroke dynamics is a biometric authentication-based system on behavior, which is an automated method in which the identity of an individual is identified and confirmed based on the way and the rhythm of passwords typed on a keyboard by the individual. The work in this paper focuses on identifying the best algorithm for implementing an authentication system with the help of machine learning for user identification based on keystroke dynamics. Our proposed model which uses XGBoost gives a comparatively higher accuracy of 93.59% than the other algorithms for the dataset used.

Windows is one of the popular operating systems in use today, while Universal Serial Bus (USB) is one of the mechanisms used by many people with practical plug and play functions. USB has long been used as a vector of attacks on computers. One method of attack is Keylogger. The Keylogger can take advantage of existing vulnerabilities in the Windows 10 operating system attacks carried out in the form of recording computer keystroke activity without the victim knowing. In this research, an attack will be carried out by running a Powershell Script using BadUSB to be able to activate the Keylogger program. The script is embedded in the Arduino Pro Micro device. The results obtained in the Keyboard Injection Attack research using Arduino Pro Micro were successfully carried out with an average time needed to run the keylogger is 7.474 seconds with a computer connected to the internet. The results of the keylogger will be sent to the attacker via email.

The Internet has gradually penetrated into the national economy, politics, culture, military, education and other fields. Due to its openness, interconnectivity and other characteristics, the Internet is vulnerable to all kinds of malicious attacks. The research uses a honeynet to collect attacker information, and proposes a network penetration recognition technology based on interactive behavior analysis. Using Sebek technology to capture the attacker's keystroke record, time series modeling of the keystroke sequences of the interaction behavior is proposed, using a Recurrent Neural Network. The attack recognition method is constructed by using Long Short-Term Memory that solves the problem of gradient disappearance, gradient explosion and long-term memory shortage in ordinary Recurrent Neural Network. Finally, the experiment verifies that the short-short time memory network has a high accuracy rate for the recognition of penetration attacks.

Many websites induce the browser to send network traffic in response to user input events. This includes websites with autocomplete, a popular feature on search engines that anticipates the user's query while they are typing. Websites with this functionality require HTTP requests to be made as the query input field changes, such as when the user presses a key. The browser responds to input events by generating network traffic to retrieve the search predictions. The traffic emitted by the client can expose the timings of keyboard input events which may lead to a keylogging side channel attack whereby the query is revealed through packet inter-arrival times. We investigate the feasibility of such an attack on several popular search engines by characterizing the behavior of each website and measuring information leakage at the network level. Three out of the five search engines we measure preserve the mutual information between keystrokes and timings to within 1% of what it is on the host. We describe the ways in which two search engines mitigate this vulnerability with minimal effects on usability.

The current authentication systems based on password and pin code are not enough to guarantee attacks from malicious users. For this reason, in the last years, several studies are proposed with the aim to identify the users basing on their typing dynamics. In this paper, we propose a deep neural network architecture aimed to discriminate between different users using a set of keystroke features. The idea behind the proposed method is to identify the users silently and continuously during their typing on a monitored system. To perform such user identification effectively, we propose a feature model able to capture the typing style that is specific to each given user. The proposed approach is evaluated on a large dataset derived by integrating two real-world datasets from existing studies. The merged dataset contains a total of 1530 different users each writing a set of different typing samples. Several deep neural networks, with an increasing number of hidden layers and two different sets of features, are tested with the aim to find the best configuration. The final best classifier scores a precision equal to 0.997, a recall equal to 0.99 and an accuracy equal to 99% using an MLP deep neural network with 9 hidden layers. Finally, the performances obtained by using the deep learning approach are also compared with the performance of traditional decision-trees machine learning algorithm, attesting the effectiveness of the deep learning-based classifiers in the domain of keystroke analysis.

User Authentication is a difficult problem yet to be addressed accurately. Little or no work is reported in literature dealing with clustering-based anomaly detection techniques for user authentication for keystroke data. Therefore, in this paper, Modified Differential Evolution (MDE) based subspace anomaly detection technique is proposed for user authentication in the context of behavioral biometrics using keystroke dynamics features. Thus, user authentication is posed as an anomaly detection problem. Anomalies in CMU's keystroke dynamics dataset are identified using subspace-based and distance-based techniques. It is observed that, among the proposed techniques, MDE based subspace anomaly detection technique yielded the highest Area Under ROC Curve (AUC) for user authentication problem. We also performed a Wilcoxon Signed Rank statistical test to corroborate our results statistically.

Keystroke Dynamics is the study of typing patterns and rhythm for personal identification and traits. Keystrokes may be analysed as fixed text such as passwords or as continuous typed text such as documents. This paper reviews different classification metrics for continuous text, such as the A and R metrics, Canberra, Manhattan and Euclidean and introduces a variant of the Minkowski distance. To test the metrics, we adopted a substantial dataset containing 239 thousand records acquired under real, harsh, and unidealised conditions. We propose a new parameter for the Minkowski metric, and we reinforce another for the A metric, as initially stated by its authors.

In the modern day and age, credential based authentication systems no longer provide the level of security that many organisations and their services require. The level of trust in passwords has plummeted in recent years, with waves of cyber attacks predicated on compromised and stolen credentials. This method of authentication is also heavily reliant on the individual user's choice of password. There is the potential to build levels of security on top of credential based authentication systems, using a risk based approach, which preserves the seamless authentication experience for the end user. One method of adding this security to a risk based authentication framework, is keystroke dynamics. Monitoring the behaviour of the users and how they type, produces a type of digital signature which is unique to that individual. Learning this behaviour allows dynamic flags to be applied to anomalous typing patterns that are produced by attackers using stolen credentials, as a potential risk of fraud. Methods from statistics and machine learning have been explored to try and implement such solutions. This paper will look at an Autoencoder model for learning the keystroke dynamics of specific users. The results from this paper show an improvement over the traditional tried and tested statistical approaches with an Equal Error Rate of 6.51%, with the additional benefits of relatively low training times and less reliance on feature engineering.