August 2026
Critical and strategic raw materials as a challenge to the EU’s strategic autonomy and security
2026, vol.18 , no.3, pp. 111-120
Article [2026-03-11]
The purpose of this article is to present the issue of growing demand for critical and strategic raw materials used in key sectors of the EU economy, as well as to relate them to the situation in Bulgaria in the context of National Research Program “Critical and Strategic Raw Materials for the Green Transition and Sustainable Development”. The methodology used is a classical historical and legal teleological approach. The study is focused on the Critical Raw Materials Act: the current lists of critical and strategic raw materials, the Act’s legal nature and some of its key components: benchmarks and the mechanism for strategic projects. The conclusion provides a critical assessment of some of the findings from the first phase of the above-mentioned Research Program.
Irena Ilieva. Critical and strategic raw materials as a challenge to the EU’s strategic autonomy and security. International Journal on Information Technologies and Security, vol.18 , no.3, 2026, pp. 111-120.
Spatial localization of Wi-Fi threat sources in critical infrastructure via RADIO-SOC event correlation
2026, vol.18 , no.3, pp. 101-110
Article [2026-03-10]
Critical-infrastructure facilities increasingly rely on dense Wi-Fi deployments, which creates exposure to rogue access points, evil-twin impersonation, deauthentication attacks and hidden clients. The paper proposes Correlated Radio-SOC Localisation (CRSL), a framework that fuses distributed RF-sensor observations, wireless-activity features, indicators of compromise and SIEM/SOAR events. The method combines localisation based on multi-sensor measurements with temporal, identity and behavioural correlation of SOC events. The framework produces classified threat findings with an estimated uncertainty region and confidence score. The proposed architecture and evaluation protocol show how radio-event fusion can improve incident attribution and accelerate operational response in protected wireless environments.
Dmytro I. Prokopovych-Tkachenko, Oleksandr Galushchenko, Yuliia Kovalenko, Mykola Mormul, Volodymyr I. Sarychev, Anton Herasymenko. Spatial localization of Wi-Fi threat sources in critical infrastructure via RADIO-SOC event correlation . International Journal on Information Technologies and Security, vol.18 , no.3, 2026, pp. 101-110.
Authentication-based secure data dissemination in 5G-enabled VANETs
2026, vol.18 , no.3, pp. 89-100
Article [2026-03-09]
With the extensive usage of Vehicular Ad Hoc Networks (VANETs) in intelligent transportation, issues such as securing and lowering the latency period become increasingly important, particularly related to potential malicious nodes. This research proposes a secure data dissemination approach for VANETs. In the suggested model, Elliptic Curve Cryptography (ECC) is used for lightweight message signing, AES is used for encryption purposes, and the VeChainThor blockchain technology is used for trustless and decentralized management of public keys. A rule-based intrusion detection system is incorporated into the edge nodes to detect any suspicious behaviour that might threaten the safety of information. The proposed approach is evaluated through simulations involving 5000 data packets, achieving an average throughput of 8.94 Mbps and a low latency of 0.021 seconds, with authentication delays.
Anupama Verma, Gulista Khan. Authentication-based secure data dissemination in 5G-enabled VANETs. International Journal on Information Technologies and Security, vol.18 , no.3, 2026, pp. 89-100.
An intelligent data-processing and machine learning workflow for urban heat assessment in smart cities
2026, vol.18 , no.3, pp. 79-88
Article [2026-03-08]
Smart city management relies on practical and repeatable ways to turn spatial data into information that planners can use. Sofia, Bulgaria, was selected as a test area for the proposed satellite-based urban heat assessment. The work uses 14,400 grid observations prepared in Google Earth Engine for June 1–September 15, 2024. The dataset combines Landsat 8/9 land surface temperature, NDVI, NDBI, MODIS albedo and geographic coordinates. These variables were examined through correlation analysis and used for regression model comparison with train-test validation, five-fold cross-validation and spatial block cross-validation. Gradient Boosting achieved the best result with R² = 0.886, mean cross-validation R² = 0.890 ± 0.004 and spatial block validation R² = 0.830 ± 0.035. An additional 2023 check confirmed the same best-performing model but with lower validation scores, showing that model performance is year-dependent. The workflow supports early-stage identification of priority areas for green infrastructure.
Nikolay Nikolov. An intelligent data-processing and machine learning workflow for urban heat assessment in smart cities. International Journal on Information Technologies and Security, vol.18 , no.3, 2026, pp. 79-88.
A classification framework for determining permissible levels of generative artificial intelligence use in engineering education
2026, vol.18 , no.3, pp. 67-78
Article [2026-03-07]
The integration of generative artificial intelligence into engineering education raises the question of how to define permissible forms of its use in different learning activities without replacing the student’s personal contribution. The aim of this study is to propose a methodology for classifying these activities according to the permissible degree of generative AI use. The methodology considers the learning objective, expected outcome, required independence, risk of substitution, and possibilities for verification and traceability. As a result, a five-level framework, L0-L4, is developed, linking each level to permissible forms of use and control mechanisms. Its practical application is illustrated through a matrix of main learning activities and examples from engineering disciplines. The framework shows that generative AI can support learning when its use is transparent and controlled but should be restricted when it replaces the knowledge and skills being assessed.
Aldeniz Rashidov, Fatme Rashidova. A classification framework for determining permissible levels of generative artificial intelligence use in engineering education. International Journal on Information Technologies and Security, vol.18 , no.3, 2026, pp. 67-78.
Bridging local and global features: A multi-backbone ensemble framework for ASD facial classification
2026, vol.18 , no.3, pp. 57-66
Article [2026-03-06]
Early non-invasive screening technologies are a paramount priority in modern healthcare for identifying complex neurodevelopmental traits characterized by social, communicative, and behavioural challenges. Recent breakthroughs in computer vision and deep learning have established automated facial image analysis as a highly viable paradigm for objective clinical screening. This study introduces a robust, optimized weighted ensemble framework that integrates the complementary architectural strengths of convolutional and transformer-based networks for binary classification of these specialized facial trait profiles. The pipeline concurrently leverages EfficientNet-B5 for localized feature scaling, Data-Efficient Image Transformers (DeiT) for long-range global self-attention, and ConvNeXt for modernized, high-performance convolutional representations. To ensure generalization and counteract dataset selection bias, a strict stratified 5-fold cross-validation scheme is enforced, followed by an optimized out-of-fold weighted probability fusion mechanism. Experimental evaluation on a benchmark dataset demonstrates that the unified ensemble achieves a state-of-the-art classification accuracy of 95.67% and an ROC-AUC of 0.9788, significantly outperforming individual standalone baselines. These empirical results validate that bridging high-frequency local textures with low-frequency global contextual relationships minimizes predictive variance, offering an accurate, stable, and scalable computational screening solution for automated clinical environments.
Anjali B., Gopinathan. S.. Bridging local and global features: A multi-backbone ensemble framework for ASD facial classification. International Journal on Information Technologies and Security, vol.18 , no.3, 2026, pp. 57-66.
Auditing the coverage of software quality & security & compliance requirements throughout the software development life cycle: A holistic approach
2026, vol.18 , no.3, pp. 45-56
Article [2026-03-05]
In recent years, due to the widespread adoption of Agile and DevSecOps approaches to software development, the increasing number of abuses and malicious actions targeting information technology-based resources and the accelerating need for software applications to adhere compliance requirements with certain standards, policies and regulations (e.g., the European Union Cyber Resilience Act or industry standards HIPAA and GDPR), the guarantee of all three – quality, the level of security and com-pliance for the needs of developing and delivering software solutions has become of significant importance. The paper presents a holistic approach to automated monitoring of software quality, security, and compliance, which has been researched and developed for the needs of one of the most growing industries, namely the FinTech industry. It introduces SDLC Auditor, a software tool designed to automatically monitor, control, and evaluate processes throughout the entire Software Development Life Cycle (SDLC) within Agile environments with regard to adherence to software quality, security, and compliance requirements. The study concludes by highlighting the advantages of the SDLC Auditor in developing stable, secure, and reliable software systems.
Zhelyana Doneva Georgieva, Rositsa Doneva, Silvia Gaftandzhieva. Auditing the coverage of software quality & security & compliance requirements throughout the software development life cycle: A holistic approach. International Journal on Information Technologies and Security, vol.18 , no.3, 2026, pp. 45-56.
Algorithmization of a stochastic switchable environment operating in discrete time
2026, vol.18 , no.3, pp. 37-44
Article [2026-03-04]
The article discussed an algorithmization of the stochastic switchable environment operating in discrete time functioning process. The goal is to create an iterative algorithm for the functioning of such a system with the possibility of node failures. The created algorithm makes it possible to increase the stability of the system and meet the security requirements of specific algorithms for bidirectional interaction for correct collaboration. The modular structure of the stochastic switchable environment operating in discrete time functional process control system software is presented. The data obtained was taken into account when forming databases of network parameters. During the experiments, the effectiveness of the developed special software was proved. To evaluate the effectiveness, data from the Bitcoin peer-to-peer payment system was used. Experiments have shown that taking into account the variability of the behavior strategy of the system nodes, the possibility of combining them into a group and adjusting the complexity of the block during mutual information coordination increases the probability of system stability by an average of 4% relative to other control systems.
O. Ja. Kravets, E. A. Chunikhina, N.S. Yakovenko, P. V. Bespalov, Yu. V. Redkin, O. O. Varlamov, N. A. Butyrina. Algorithmization of a stochastic switchable environment operating in discrete time. International Journal on Information Technologies and Security, vol.18 , no.3, 2026, pp. 37-44.
Explainable cross-layer machine learning for enterprise WLAN auditing
2026, vol.18 , no.3, pp. 25-36
Article [2026-03-03]
This paper presents an explainable cross-layer machine learning method for auditing enterprise and campus wireless local area networks. It combines passive radio and Medium Access Control evidence with service, mobility, security and configuration indicators to identify anomalous windows, infer root causes and generate audit scores for operator review. The learning process uses unsupervised anomaly admission and supervised root-cause classification, while the reporting layer produces evidence-supported recommendations. Evaluation is conducted with CrossAudit-WLANSim, a Python-based discrete-time simulator configured for three enterprise sites, twelve access points and 69120 audit windows. Under site drift, the drift-aware configuration reaches an anomaly F1-score of 0.770 and an eight-state macro-F1 of 0.855, outperforming a network-only baseline and reducing false-positive alarms.
Victor Stoynov. Explainable cross-layer machine learning for enterprise WLAN auditing. International Journal on Information Technologies and Security, vol.18 , no.3, 2026, pp. 25-36.
Session-state payload size and autoscaling behaviour of MVC applications in a Kubernetes testbed
2026, vol.18 , no.3, pp. 15-24
Article [2026-03-02]
This paper evaluates the scaling behaviour of Model-View-Controller (MVC) applications in a Kubernetes testbed, focusing on external session-state payload size and autoscaling behaviour. A Redis-backed MVC deployment is tested under burst workload with three payload sizes, three replica counts, and three repetitions per condition. A second experiment validates Kubernetes Horizontal Pod Autoscaler (HPA) and Kubernetes Event-driven Autoscaling (KEDA) with Prometheus under a CPU-heavy burst workload. Results show that the 100 KB payload reduces throughput and increases p95 latency and failed-request rates, while additional web replicas do not remove the shared-state cost. Both HPA and KEDA produced real pod scaling. The findings show that MVC scalability depends on payload size, shared state-store capacity, workload shape, and scaling signal.
Meriton Ibraimi, Agon Memeti. Session-state payload size and autoscaling behaviour of MVC applications in a Kubernetes testbed. International Journal on Information Technologies and Security, vol.18 , no.3, 2026, pp. 15-24.