Search

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

Understanding the distinct characteristics of unidentified Internet users is helpful in various contexts, including digital forensics, targeted advertising, and user interaction with services and systems. Keystroke dynamics (KD) enables the analysis of data derived from a user’s typing behaviour on a keyboard as one approach to obtain such information. This study conducted experiments on a developed dataset that recorded samples of typing in five different mother tongues to determine Internet users’ mother tongue. Based on only a few KD features and machine learning techniques, 82% accuracy was achieved in recognising an unknown user’s mother tongue. This research highlights the potential for KD as a reliable method for identifying the mother tongue of Internet users, with implications for various applications such as improving digital forensic investigations, targeted advertising strategies, and optimising user experiences with online services.

In modern industry, anomaly detection is an important part of safety and productivity management. Early anomaly detection could allow for timely interventions, preventing malfunctions and reducing risks for human workers and machines. This work aims to deliver an overview of the use of machine learning for anomaly detection in industrial environments, highlight the state-of-the-art, and discuss challenges and prospects for future research. Existing approaches, methodologies, and results related to anomaly detection are summarized, focusing on the application of machine learning for different types of industrial anomalies. Research findings indicate that, despite the current advances, there is still room for improvements and developments in machine learning-based anomaly detection in industrial environments, designating an important future field of research.

Knowing some characteristics of an unknown user is useful information for security and commercial purposes. One of the acquired characteristics is the user’s native language, and its recognition can be achieved with data derived from the text he/she types, since text is the most widespread means of communication between Internet users. Keystroke dynamics, which leverages data derived from how user types, ensures that no sensitive data are leaked. In this work, data from the daily typing of users of five different native languages are collected, keystroke dynamics features are extracted, the most suitable ones are selected using a feature selection algorithm, well-known machine learning models and a boosting algorithm are used, and a rate of correct prediction that exceeds 90% is achieved. Knowing a user’s native language can help strengthen authentication systems, make better use of online services, and protect unsuspecting users from falling victim to fraud.