Dynamic Touchstroke Analysis with Explainable Artificial Intelligence Tree-Based Learners

As mobile devices become integral to daily life, robust authentication methods are essential for ensuring security. Traditional methods like personal identification numbers and swipe patterns remain vulnerable to social engineering attacks. To address these risks, this study investigates behavioural biometrics, specifically touch-stroke dynamics, as a transparent and secure alternative. By leveraging unique user interaction patterns, such as touch speed and pressure, this approach provides a distinctive means of authentication. Although various machine learning techniques are available for touch-stroke analysis, the interpretability of classification decisions is vital. This paper implements explainable artificial intelligence with tree-based learners, specifically decision trees and random forests, to enhance the transparency and effectiveness of touch-stroke dynamic authentication. Performance evaluations show that random forests achieve equal error rates (EER) between 0.03% and 0.05%, and decision trees yield EERs between 0.02% and 0.07%, demonstrating a balance between security and interpretability for mobile authentication.

Review and Enhancement of VoIP Security: Identifying Vulnerabilities and Proposing Integrated Solutions

The prolific use of Voice over Internet Protocol (VoIP) causes this system’s vulnerabilities to become a major concern for individuals or organizations. Based on this concern, this paper aims to provide a comprehensive analysis of the cyber threats and attacks in VoIP systems. VoIP offers several benefits and advantages; however, it poses significant security risks which can cause serious consequences. At the beginning of this paper, an overview of VoIP, including its architecture, components, protocols and advantages are discussed. Following this, attack vectors and component vulnerabilities are examined, and types of security threats are categorized into different sections for clarity. The types of attacks under discussion involved Denial-of-Service (DoS) and Man-in-the-Middle (MITM) attacks, spoofing threats, registration and call hijacking, Spam over Internet Telephony (SPIT), vishing, malware and toll fraud. Subsequently, existing security solutions for VoIP systems are reviewed, highlighting their strengths, weaknesses and applicability. While some solutions are effective in protecting VoIP, a lack of robustness still exists. Hence, this paper proposes an enhanced security method: the combination of Virtual Private Networks (VPNs) and firewalls within VoIP systems. This combination can reduce potential cyber risk by enhancing data privacy and protection, and overall system security.

Autonomous Robot Navigation System Workflow for Monitoring and Maintenance in Industry 4.0 Applications

Autonomous navigation in factories faces a different challenge with a lack of GPS, frequently changing environment, and human interference. Current methods employed include autonomous guided vehicles, which require extensive setup and lack flexibility, making it unsuitable for frequently changing environments. Prohibiting the adoption of an autonomous mobile robot is the slow mapping time and cost. A method of autonomous navigation combining computer vision with path-planning algorithms is presented. This method uses cameras attached to the environment for navigation and not on the robot to leverage security cameras commonly available. Out of the four aspects of navigation, only three were successful, namely perception, localisation, and cognition. Mapping via grayscale thresholding is found faster than simultaneous localisation and mapping but is less accurate because it is dependent on lighting. Faster region-based convolutional neural network or You Only Look Once version 4 (YOLOv4) found no difference because the travel time is significantly longer than the processing time of both. The proposed method using A* path planning with Euclidean heuristic successfully reaches the goal for at least 30 repeats. Navigational abilities are still limited in real-world settings because of accumulation of error from odometry and inertial measurement unit sensors and lack of localisation feedback.

Sharing Business Data Securely

Federated data spaces (FDSs) represent an innovative approach to foster sovereign and interoperable data sharing across various business domains, promising substantial opportunities for value creation. The European Gaia-X initiative has emerged as a key driver in promoting FDS developments, particularly through its emphasis on data sovereignty and collaborative innovation. Effective design and operation of FDSs require a wide array of skills, expertise, services and technological components, creating a complex landscape for participating organisations. In this paper, we explore the technical and economic roles necessary for the successful implementation of FDSs, focusing on insights derived from two mobility use cases. Through interviews with experts engaged in a Gaia-X project, we identify 39 distinct roles, which we further abstract into eight meta-roles. These roles illustrate the structure and dynamics of inter-organisational collaboration in FDSs. Our analysis contributes to existing knowledge by illuminating the inter-organisational networks in FDSs, with a specific focus on the roles that support technical integration and economic value generation.

Decoding Consumer Behaviour in Indonesian E Commerce: A Stimulus-Organism-Response Analysis

Indonesia holds a significant position in Southeast Asian e-commerce, witnessing notable shifts in consumer shopping patterns owing to the rapid expansion of online markets. This study concentrates on understanding e-commerce dynamics within Indonesian suburban areas. This research aims to unravel the hindering factors in Indonesian e-commerce, employing the Stimulus-Organism-Response framework to decode the intricate relationships between stimuli, organisms, and responses. This study endeavours to comprehend the intricate perceptions and behavioural tendencies exhibited by a cohort of 280 individuals by implementing a targeted quantitative questionnaire. The investigation seeks to scrutinize the impact of security, privacy, perceived risk, and cognitive trust on the attitudes and behavioural intentions of suburban consumers engaging in e-commerce activities. Employing SmartPLS as the analytical framework and utilizing Partial Least Squares Structural Equation Modelling (PLS-SEM), the research aims to investigate the causal relationships among key factors in the Indonesian suburban e-commerce industry. With a focus on the suburban population, this empirical study will offer comprehensive insights into the intricate dynamics of e-commerce. The findings are expected to contribute meaningful insights to the growing domain of e-commerce research and offer practical recommendations to foster the development of a resilient and thriving e-commerce ecosystem in Indonesia.

E-Commerce Security Issues, Then and Now

Simon Moorhead’s recent historical reprint (December 2024) revisiting Dez Blanchfield’s December 2000 paper in TJA on e-commerce security has stimulated this author to make additional comments on the weaknesses of major websites and of email systems today in permitting fraud and deception, in comparison to 24 years ago.