November 2025
Quantitative detection of disinformation patterns using semantic vector analysis
2025, vol.17 , no.4, pp. 119-126
Article [2025-04-12]
This study examines the semantic coherence of disinformation headlines using publicly available machine learning tools. By applying sentiment, temporal, and security classifiers, the research confirms that syntactically distinct but thematically aligned headlines cluster in a shared semantic space. The findings support Claire Wardle’s concept of information environments and highlight the enduring importance of human judgment in combating information manipulation.
Valeri Nikolov, Michael Dimitrov. Quantitative detection of disinformation patterns using semantic vector analysis. International Journal on Information Technologies and Security, vol.17 , no.4, 2025, pp. 119-126.
Fundamentals of a theoretical model of small country security
2025, vol.17 , no.4, pp. 111-118
Article [2025-04-11]
The issue of building a state security model is immanently related to the factors that influence foreign policy and security policy. This applies also to the criteria by which to classify a state as “small” using scientific methodology. This process requires serious scientific research, public and even political work, as well as participation in discussions where alternative opinions and assessments are presented, but also specific proposals for measures for establishing such a model. This article does not claim to answer all the questions but rather seeks to lift the “curtain” a little and provoke a discussion, in view of the enormous challenges the world faces in modern times.
Todor Koburov. Fundamentals of a theoretical model of small country security. International Journal on Information Technologies and Security, vol.17 , no.4, 2025, pp. 111-118.
Cluster-based tristate aggregation method for dependability evaluation of electrical systems
2025, vol.17 , no.4, pp. 99-110
Article [2025-04-10]
This paper presents a novel approach for dependability evaluation of power supply systems based on discrete state aggregation. The proposed method, called the Tristate Cluster Aggregation Model (TRICAM), groups system components into fixed clusters, where each component can be in one of three operational states: fully operational (100%), partially operational (50%), or failed (0%). The cluster's overall state is determined using rule-based logic that reflects real-world failure propagation and degradation. By computing the probabilities of state transitions at the component level and aggregating them, the method produces a compact cluster-level Markov model. TRICAM significantly reduces the dimensionality of the state space compared to conventional models, enabling efficient analysis of large systems. This approach provides a scalable and interpretable framework suitable for evaluating reliability and guiding maintenance or reconfiguration strategies in modern power infrastructures.
Dmytro Stetsiuk, Dmitry Maevsky, Elena Maevskaya, Viacheslav Lavrynenko, Kvitchuk Vitalii. Cluster-based tristate aggregation method for dependability evaluation of electrical systems. International Journal on Information Technologies and Security, vol.17 , no.4, 2025, pp. 99-110.
Enhancing phishing site detection and prevention through machine learning with image classification
2025, vol.17 , no.4, pp. 87-98
Article [2025-04-09]
Distinguishing expertly designed phishing sites from genuine ones is difficult, likely contributing to the continued victimization of users by these attacks. The challenge of creating a universal algorithm to detect these malicious pages has resulted in the development of various tools to protect users. This paper introduces an innovative method for detecting and preventing phishing websites using machine learning, which is implemented in a newly developed browser plugin called NotPwned. Additionally, tools have been created for data collection and training computer vision models. A classifier has been designed to identify login forms based on submitted screenshots. The most well-known algorithms for object detection in images have been analysed and compared. Furthermore, a model has been trained to recognize different logos. The research concludes with a comparison of the system's capabilities against those of competing solutions, demonstrating the effectiveness of the proposed method and the resulting product.
Kaloyan Manev, Milen Petrov, Adelina Aleksieva-Petrova. Enhancing phishing site detection and prevention through machine learning with image classification. International Journal on Information Technologies and Security, vol.17 , no.4, 2025, pp. 87-98.
Automata model of a system with distributed ledger technology based on a blockchain
2025, vol.17 , no.4, pp. 79-84
Article [2025-04-08]
The article discussed an automata model of the functioning process of a system with distributed ledger technology based on a blockchain. The goal is to develop a special mathematical system with a distributed ledger based on a blockchain, taking into account the specifics of implementing algorithms for mutual information coordination, the possibility of combining individual nodes into groups, and implementing alternative strategies based on the development of appropriate models and algorithms that ensure increased stability in their operation. Automata theory was used, theory and methods of mutual coordination were applied, and the mechanism of the functioning process of a system with a distributed register was implemented. An automata model has been obtained and investigated. Thus, an automata model of the distributed ledger technology blockchain system node functioning process has been developed, which differs from the node representation by a finite state machine with a variable structure and a linear tactic with the possibility of implementing non-standard functions: the formation of a branch of processed data and a temporary blockage attack, and provides for obtaining the dependence of the sequence of changing the node's behaviour strategy options on the conditions of the environment it interacts with.
O. Ja. Kravets, Ali Husein, D. V. Getmanskaia, Mustafa Jaafar Baqer Al-Imari, I. A. Chernoivanenko, Yu. V. Redkin, O. O. Varlamov. Automata model of a system with distributed ledger technology based on a blockchain. International Journal on Information Technologies and Security, vol.17 , no.4, 2025, pp. 79-84.
Real-time traffic-based detection of XSS vulnerabilities via bidirectional HTTP traffic analysis
2025, vol.17 , no.4, pp. 69-78
Article [2025-04-07]
Cross-site Scripting (XSS) vulnerabilities continue to compromise web application security due to delayed detection by periodic scans. This paper proposes a novel real-time, traffic-based detection system that inspects HTTP request-response flows to verify exploitability dynamically. Unlike existing solutions that rely on static rules or post-analysis, the introduced proxy-based framework passively tracks and correlates incoming requests with their reflections in outgoing responses, specifically examining executable contexts. Evaluation using established testing suites demonstrates that the system accurately identifies 66% of exploitable XSS vulnerabilities confirmed by dynamic scanners, with no false positives. The results highlight that real-time traffic analysis effectively complements existing tools, providing immediate and actionable vulnerability insights, significantly narrowing the window for attackers and accelerating the defensive response.
Anas Roubi, Muhalim Mohamed Amin. Real-time traffic-based detection of XSS vulnerabilities via bidirectional HTTP traffic analysis. International Journal on Information Technologies and Security, vol.17 , no.4, 2025, pp. 69-78.
Privacy-preserving digital twin technologies for smart cities: Balancing utility and data protection
2025, vol.17 , no.4, pp. 57-68
Article [2025-04-06]
Digital twins (DTs) have emerged as transformative techn ologies for smart cities, providing real-time virtualization of physical infrastructure and enhancing decision-making capabilities. However, their extensive data collection and integration raise significant privacy concerns. This study introduces a novel privacy-preserving framework for smart city digital twins that balances utility and data protection through multilayered privacy mechanisms. We propose a hybrid architecture integrating differential privacy, federated learning, and secure multi-party computation to protect citizen privacy while maintaining analytical utility. The framework was implemented and evaluated using three real-world datasets: the NYC Open Data transportation feeds, SmartSantander IoT sensor network, and London Air Quality Network. Our comprehensive evaluation measured privacy protection, data utility, computational overhead, and scalability across various urban scenarios. Results demonstrate that our approach achieves 94.7% of the analytical accuracy of non-private systems while providing formal privacy guarantees (ε=2.1). Performance analysis shows the framework can handle real-time data processing with less than 152ms latency for critical smart city applications.
Mahmoud Mohamed, Dina Mohamed, Mohamed M H Maatouk. Privacy-preserving digital twin technologies for smart cities: Balancing utility and data protection. International Journal on Information Technologies and Security, vol.17 , no.4, 2025, pp. 57-68.
Formalized method of inter-machine interaction of intelligent particles with a series of behavioural scenarios of particles and the swarm as a whole
2025, vol.17 , no.4, pp. 45-56
Article [2025-04-05]
The article is devoted to the development of a formalized method of inter-machine interaction of intelligent particles, which includes a series of scenarios for the behaviour of individual particles and the swarm as a whole. The main emphasis is placed on the formation of model and algorithmic support for a promising multi-agent technology based on the principles of communication between particles. Various behaviour scenarios of particles during their life cycle are considered, from emission to deposition through propagation, with the application of functions of data collection, transmission, and reception within the swarm. Graph theory and methods of pulse-width modulation are applied for modelling the interaction. Algorithms for controlling the operating modes of particles are presented, optimized for specific stages of experimental research. The results of efficiency analysis of the proposed approaches are provided, as well as recommendations for the design of communication technologies for swarm systems.
Igor V. Kovalev, Vasiliy V. Losev, Mikhail V. Saramud. Formalized method of inter-machine interaction of intelligent particles with a series of behavioural scenarios of particles and the swarm as a whole. International Journal on Information Technologies and Security, vol.17 , no.4, 2025, pp. 45-56.
Topic and style: Authorship attribution with multi-vector meta-features and stacked classifier
2025, vol.17 , no.4, pp. 33-44
Article [2025-04-04]
Authorial rights are meaningful only when a document is promptly attributed to its legitimate creator. While an author’s unique topical preferences may pinpoint them within a group of thematically-diverse writers, attribution becomes considerably challenging in cases such as judicial opinions – e.g., attributing a criminal case judgement to one among hundreds of judges heading criminal courts – due to overlapping contextual jargon. In such situations, integrating both topical and stylistic cues can enhance the reliability and generalisability of authorship attribution. This work proposes a custom stacking ensemble model trained on diverse aspects of text, later giving rise to novel features: Multi-Vector Meta-Features. The proposed method demonstrates statistically significant boosted accuracy scores across three out of four datasets, outperforming baseline model and recent stacking ensemble models.
B. Lavanya, R. Sowmiya. Topic and style: Authorship attribution with multi-vector meta-features and stacked classifier. International Journal on Information Technologies and Security, vol.17 , no.4, 2025, pp. 33-44.
Analysis and evaluation of satisfaction and preferences regarding the use of artificial intelligence in education
2025, vol.17 , no.4, pp. 23-32
Article [2025-04-03]
This study presents a study aimed at analyzing and evaluating the satisfaction and preferences of students and teachers regarding the use of artificial intelligence (AI) in the educational process. Surveys and interviews were conducted to collect data on the perception of various AI-based solutions, focusing on factors such as usefulness, ease of use, interaction quality, and trust in outcomes. An adapted ranking method based on weight coefficients was applied to assess preferences for specific AI tools, enabling the analysis of trends over time. The results provide an objective basis for optimizing the integration of AI in education and formulating recommendations for educational institutions to enhance the effectiveness of the learning process. The findings are expected to contribute to a better understanding of AI’s impact on education and support future initiatives for its integration.
Aldeniz Rashidov. Analysis and evaluation of satisfaction and preferences regarding the use of artificial intelligence in education. International Journal on Information Technologies and Security, vol.17 , no.4, 2025, pp. 23-32.