This study aims to describe both existing and new capabilities of the system of PROSTOR and create conditions for more convenient use of the program. PROSTOR is a program designed to fi nd optimal ways of transporting goods between hubs. The author introduce capabilities of the program including innovative features such as automatic data conversation based on location of transport hub. This addition allows each user to determine the dimensions of a transportation problem experiment and solve the problem within PROSTOR. This helps researchers to work with the program easer.

Also the ability to increase product dimension was added to the program. This innovation is crucial for improving accuracy of the solutions generated by PROSTOR as it combines optimal ways of transporting goods and actual geographic and product features of hubs. This improvement in the program is necessary because it takes into account the complexity of building relationships in a real transportation system.

The implementation of these features into the PROSTOR system has enhanced its eff ectiveness for researchers studying the development of transport systems. Now the obtained results provide a more accurate description of the transport sector leading to higher-quality forecasts. These program modifi cations not only improve the precision of experimental outcomes but also simplify user interaction with the system.

The increasing complexity and scale of network attacks necessitates the transition from traditional signature intrusion detection systems (IDS) to more adaptive approaches based on machine learning methods. This study presents a comparative analysis of the eff ectiveness of classical machine learning algorithms and the automated machine learning (AutoML) framework AutoGluon in solving the problem of multiclass classifi cation of network traffi c. The publicly available CICIDS2017 dataset was used as an experimental base, which includes both legitimate connections and various types of attacks that simulate real-world network conditions.

An analysis of network characteristics and their discriminative ability is carried out, as well as a detailed assessment of model performance using the metrics of general accuracy, F1-measure, and training time. The results showed that ensemble algorithms, in particular Random Forest and AutoGluon, achieve the highest overall accuracy (more than 99.5%). At the same time, the detection effi ciency of minor classes of attacks, such as SQL Injection and cross-site scripting (XSS), is critically low. It has been established that this problem is caused not only by a strong data imbalance, but also by the characteristics of the attacks themselves, which are often disguised as legitimate traffi c and do not form pronounced statistical anomalies.

Thus, the study demonstrates the potential and limitations of using AutoML frameworks in the fi eld of cybersecurity. The practical signifi cance of the work lies in the possibility of reducing the development time of intrusion detection systems (IDS) while maintaining high accuracy, and the prospects for further research are related to the integration of class balancing methods and the development of hybrid models to improve the recognition of rare attacks. 

This study addresses the challenge of automating information extraction from textual sources to support investment decision-making through geospatial frameworks. An integrated analytical system has been developed that leverages advances in natural language processing, deep learning, and geographic information science to identify and classify investment projects from diverse open-access documents. The proposed approach employs a sequence-to-sequence neural architecture capable of simultaneously performing categorical analysis (determining project development phases) and numerical prediction (estimating project value). These fi ndings underscore the importance of task-specifi c optimization strategies in mixed-type information processing. The system demonstrates viable applicability for portfolio assessment, strategic resource allocation, and geospatial economic monitoring. Future development pathways include curriculum-based learning approaches, cross-task knowledge transfer, and enhanced model transparency mechanisms. 

Currently, due to the digitalization of processes and the growing number of cyber threats, many companies are in need of competent specialists with the necessary information security skills. The article off ers a modern digital software product based on virtual reality technology. Virtual simulators can be actively used in the educational process. The use of such technologies makes it possible to carry out pilot industrial work in an environment as close to reality as possible. The virtual laboratory is a set of interactive models in a three-dimensional virtual space and has a wide range of practical tasks aimed at timely response to information security incidents and their prevention. The article presents an analysis of existing software tools and virtual simulators in the fi eld of Information Security. Conclusions are drawn about the need to develop a virtual laboratory for information security at the informatization facility. The algorithm of the user’s work with the virtual laboratory is presented. The interface forms and fragments of the virtual laboratory program code are described. The paper presents the stages of program development and the results of testing a virtual laboratory for information security at an informatization facility. The testing of the virtual laboratory confi rmed the importance of using the simulator in the educational process as a tool for obtaining professional competencies. Based on the results of the statistical data of the experiment, it can be concluded that the use of an exclusively virtual laboratory has reduced the time spent on laboratory work by 30 minutes, while improving the quality of the absorbed material. 

In this paper, we aim to develop an efficient workflow for critical questions generation from argumentative texts based on argumentation schemes and modern large language models. We have prepared two corpora for this task: an English corpus with 200 argumentative texts and a Russian corpus with 92 texts (54 news texts, 38 essays/analytics). We have also carried out an experiment with three different models for critical questions generation: mistralai/Mistral-7B-Instruct-v0.3, Qwen/Qwen2.5-7B-Instruct, google/flan-t5-large. The results have shown that the google/flan-t5-large model is the best for critical questions generation for the English corpus (composite score 0.361), while for the Russian corpus, it was the best performance of the mistralai/Mistral-7B-Instruct-v0.3 model (composite score 0.285, BERTScore 0.722). The critical questions generation module can be used as a component in information reliability analysis systems.