27 December 2024 in Bulletin of Shakarim University. Technical Sciences
Threat Intelligence (TI) is information about current or emerging threats to information security that is used to enhance the protection of organizations. TI systems collect and analyze data from various sources, including open sources, closed sources, as well as data obtained from partners and clients. Analysis of TI systems is the process of evaluating the effectiveness of these systems in data collection and analysis, as well as in providing useful information for decision-making in the field of information security. In the modern digital world, where information security threats are becoming increasingly complex and sophisticated, the analysis of Threat Intelligence (TI) systems is becoming crucial for ensuring the security of information resources. Threat Intelligence is the process of collecting, analyzing, and interpreting data on information security threats aimed at identifying threats to information security. In this context, the analysis of TI systems serves as an important tool for effectively understanding threats and taking measures to prevent them. This article is dedicated to examining the features, advantages, and disadvantages of Threat Intelligence system analysis. For example, TI analysis can be used to evaluate the effectiveness of an intrusion detection system. (IDS). Analysis can identify which types of attacks an IDS can detect and which it cannot. Based on the analysis results, a decision can be made regarding the need to upgrade the IDS system or to add additional protective measures.
25 January 2026 in Bulletin of Shakarim University. Technical Sciences
This article examines the problem of optimizing security policies in software-defined networks (SDN). The authors propose solving this problem using NSGA-II, an efficient algorithm for evolutionary optimization of multiple objectives. The proposed approach aims to achieve a balance between the need to strictly enforce network security and the availability of limited computing resources. Particular attention is paid to factors such as data transmission latency and TCAM table size, which significantly affect the effectiveness of traffic filtering. Based on the model developed in the article, which includes threat probability assessments, objective function normalization methods, and the use of penalty coefficients for rule conflicts, optimization was performed across three key parameters: attack risk, network latency, and TCAM load. The simulation covered three network operation scenarios-normal, mixed, and attack-using Mininet and Ryu packets. A comparison of the proposed method with differential evolution (DE) and a greedy algorithm (Greedy) showed that NSGA-II achieves optimal solution distribution along the Pareto frontier, converges faster, and maintains filtering accuracy. The paper also presents visualization of generational transitions, tradeoff graphs, and load profiles. The conclusion discusses the potential for integrating the proposed model with ONOS and OpenDaylight controllers, and discusses the feasibility of using hybrid solutions based on Deep Reinforcement Learning, Federated Learning, and Explainable AI.
25 January 2026 in Bulletin of Shakarim University. Technical Sciences
This study presents a new intelligent system based on deep learning methods for the automatic detection of hate speech in the Kazakh language. Particular attention is paid to the specific nature of Kazakh as a resource-poor language, where the limited linguistic data poses significant challenges in building reliable models. A multilingual data corpus covering a wide range of speech contexts was generated and preprocessed using various online sources-social media, forums, and news portals. To improve efficiency and generalization performance, a hybrid architecture was proposed, including convolutional neural networks (CNNs), bidirectional long short-term memories (BiLSTMs), and Transformer attention mechanisms. An evaluation using precision, recall, F1-criterion, and accuracy metrics demonstrated the superiority of the proposed model over traditional machine learning algorithms. The results of the study make a significant contribution to the development of automatic content moderation systems and promote the creation of a safer, inclusive, and linguistically sensitive digital space for Kazakh-speaking users.
25 May 2026 in Bulletin of Shakarim University. Technical Sciences
In the context of the active and uncontrolled dissemination of information in the digital environment, especially on social media and news aggregators, the task of automatically identifying fake news has become especially relevant. The growing volume of user-generated content and the high speed of its distribution significantly complicate manual information verification, necessitating the use of machine learning methods. The aim of this study is to analyze, comparatively evaluate, and optimize baseline machine learning models for fake news detection, focusing on hyperparameter selection, computational efficiency, and interpretation of classification results. This study utilizes the ISOT Fake News Dataset, a text dataset containing Englishlanguage news items with binary labels labeled «true» and «false», cleaned and vectorized using the TF-IDF method. The study implemented and analyzed logistic regression, decision tree, random forest, and gradient boosting models. Classification quality was assessed using the following metrics: Accuracy, Precision, Recall, F1-score, as well as ROC analysis and the area under the curve (AUC). It was shown that the gradient boosting model provides the highest classification accuracy, while logistic regression demonstrates comparable quality with significantly lower computational costs and training time. Additionally, the study included data leakage monitoring and an analysis of the causes of inflated quality metrics, ensuring the correct interpretation of the results. The findings confirm that optimized classical machine learning models are capable of providing highquality fake news detection and can be considered a resource-efficient alternative to more complex neural network approaches in applied cybersecurity and information flow monitoring.