FTFariza B. Tebueva

Fariza B. Tebueva

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Fariza B. Tebueva has a total of 39 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • An overview of modern cloud container technologies and a comparative analysis of their orchestration tools

    by L.T. Kusepova, A.B. Ospanova, F.B. Tebueva, A. Amandykkyzy, E. Nazyrova, Y.A. Tuleshov

    In large-scale cloud environments, virtualization plays an important role in application deployment, load distribution, and efficient management of platform resources and services. Along with traditional methods such as virtual machines, the use of containerization technology is becoming increasingly popular. Containers provide a simpler and faster way to virtualize than virtual machines, speeding up the process of deploying and managing applications in an isolated environment, allowing them to run and ensure efficient use of resources. Containers are also the best option for developers who test application components and microservice architecture. As a result, containerization is becoming the preferred choice for modern cloud environments and business needs. Accordingly, this work is focused on the study of modern and currently known containerization technologies. The article provides an overview of modern containerization and orchestration technologies, focusing on the performance parameters of containers, supported operating systems, scaling capabilities, replication and resource management, classification by container type, and analysis of these tools. The work presents well-known container solutions such as Docker, Docker Swarm, Kubernetes (K8s), Marathon and others, and analyzes based on criteria such as types of workloads, ease of management, file system isolation, network isolation, processor scheduling, limiting the use of system resources, save/restore capability, live migration capability, autoscaling levels, supported templates, and explores the advantages and disadvantages of each technology. This work will be useful for information technology professionals in choosing the most suitable tool for deploying applications and implementing their cloud strategies.

  • Open Access

    Simulation model of a scalable method for detecting multi-vector attacks taking into account the limitations of computing and information resources of IoT devices

    by V. I. Petrenko, F. B. Tebueva, M. G. Ogur, G. I. Linets, V. P. Mochalov

    Objectives. The study sets out to develop a scalable method for detecting multi-vector attacks on Internet of Things (IoT) devices. Given the growth of security threats in IoT networks, such a solution must provide high accuracy in detecting attacks with minimal computing costs while taking into account the resource constraints of IoT devices.Methods. The developed hybrid neural network architecture combines convolutional networks for spatial dependence analysis and long short-term memory networks or gated recurrent units representing types of recurrent neural networks for analyzing time dependencies in network traffic. Model parameters and computational costs are reduced by pruning. A blockchain with a proof of voting consensus mechanism provides secure data management and decentralized verification.Results. Experiments on the CIC IoT Dataset 2023 showed the effectiveness of the model: the accuracy and F1 measure were 99.1%. This confirms the ability to detect known and new attacks in real time with high accuracy and completeness. Processing time is reduced to 12 ms, while memory usage is reduced to 180 MB, which makes the model suitable for devices with limited resources.Conclusions. The developed model is superior to analogues in terms of accuracy, processing time, and memory usage. Hybrid architecture, pruning, and decentralized verification provide effectiveness against multi-vector IoT threats.


  • Open Access

    INVESTIGATION OF VULNERABILITIES IN INTERNET OF THINGS PLATFORMS AND PROTOCOLS USING PENETRATION TESTING METHODS

    by К. М. Сагиндыков, Д. Ж. Сатыбалдина, Ф. Б. Тебуева, T. Aidynov, A. Shaikhanova, Т. А. Айдынов, А. К. Шайханова

    The paper presents research findings related to the security of widespread Internet of Things (IoT) platforms and protocols, based on the analysis of existing vulnerability databases and practical penetration testing of IoT device networks using modern methods. An algorithm for collecting and extracting relevant data from the Common Vulnerabilities and Exposures (CVE) database has been developed. Additionally, a web interface for an interactive CVE table was created, facilitating the processing and visualization of large volumes of data in a convenient and clear format. The conducted analysis aimed to identify the most critical vulnerabilities that should be minimized through the introduction of a new authentication protocol for IoT devices and to define specific requirements for the protocol targeting identified vulnerabilities. During penetration testing of wireless networks, significant vulnerabilities were discovered in the examined IoT devices and the LoRaWAN wireless network. As a result, a dataset containing a list of IoT system vulnerabilities extracted from the CVE glossary, including descriptions of attack vectors and severity based on the Common Vulnerability Scoring System (CVSS), was compiled, along with practical recommendations for mitigating the vulnerabilities.


  • PROBLEM-ORIENTED SYSTEM FOR MONITORING AND RESPONDING TO MULTIVECTOR ATTACKS IN A DECENTRALIZED INTERNET OF THINGS ENVIRONMENT

    by F. B. Tebueva, V. I. Petrenko, D. Zh. Satybaldina, M. G. Ogur, T. M. Guseva

    Objective: to enhance the effectiveness of monitoring and responding to multivector attacks in a decentralized Internet of Things (IoT) environment by integrating federated learning, deep autoencoders, and the distributed IOTA ledger. The priorities include accurate attack detection, minimizing false positives, reducing response time, and preserving data privacy. Method: a problem-oriented system was developed, combining local monitoring on IoT nodes with autoencoders for anomaly detection, federated learning using the FedAvg algorithm for collective model updates, and decentralized alert dissemination via the distributed IOTA ledger. The system implements secure exchange of model parameters, digital message signing, and asynchronous response through a publish/subscribe network. Results: experimental studies on the real N-BaIoT dataset simulating multivector attacks demonstrated high detection accuracy (approximately 95%), achieving an F1-score above 94%, with false positive rates around 4%. The system's response time did not exceed 5 seconds, significantly improving operational reaction to attacks. Federated learning provided steady improvement in model quality considering data distribution and heterogeneity. The architecture proved scalable, fault-tolerant, and capable of effectively detecting complex threats across multiple system levels. Practical value: the solution is implementable in industrial IoT, smart cities, and medical networks to enhance cybersecurity while maintaining privacy and reducing network load. Scientific novelty: the study presents a comprehensive synthesis of federated learning, deep autoencoders, and distributed ledger technology for effective monitoring of multivector attacks in decentralized IoT environments. The proposed approach combines the advantages of distributed learning and blockchain mechanisms to achieve high adaptability, accuracy, and security in rapidly growing and diverse IoT infrastructures

  • Open Access

    Model of trusted interaction of agents in decentralized cyber-physical environmentv

    by V. I. Petrenko, F. B. Tebueva, I. V. Struchkov, S. S. Ryabtsev, C. C. Рябцев

    Objective. The purpose of the work is to increase the efficiency of the functioning of agents of a cyber-physical system in the presence of agents with incorrect or malicious behavior. The goal is achieved by establishing a trusted interaction between agents and quick detection of malicious impact.Method. Trusted interaction is carried out using distributed ledger technology and agent confidence indicators. The novelty of the proposed solution lies in the fact that information about the actions of agents is stored and aggregated using smart contracts at specified time intervals. Each agent keeps a local copy of the agent interaction chain. If several agents interact with each other, then they exchange information stored in their copies of the ledger.Result. To test the proposed method, we implemented it in C++. For the experiments, the scenario of collective perception by agents of a decentralized cyber-physical environment in a specialized simulation program Contiki Cooja was used.Conclusion. The method implemented using the solutions proposed in this work showed higher efficiency than the method based on the dynamic calculation of the confidence index. The proposed solutions can be applied not only in cyber-physical systems, but also in any other systems with decentralized control.


  • Distribution of tasks in a clustered field of goals for homogeneous and heterogeneous UAV groups

    by Federal State Autonomous Educational Institution of Higher Education «North Caucasian Federal University» (NCFU), Vyacheslav Petrenko, Fariza Tebueva, Vladimir Antonov, Artur Sakolchik, Belarusian State University (BGU)

    This work is devoted to the distribution of tasks in groups of unmanned aerial vehicles (UAVs) under conditions of a significant excess of the number of tasks over the number of agents. The main tasks solved by UAVs: survey and reconnaissance of territories, detection of dangerous objects or places of emergencies, search for victims, etc. The efficiency of solving the problems listed above achieved by the simultaneous use of a group of UAVs, the ele-ments (agents) of which can carry out the tasks of inspecting and scanning various areas of space in parallel. The article proposes an iterative method for distributing tasks in a group of UAVs with a significant excess of the num-ber of tasks over the number of agents (5-20 times). The proposed method for heterogeneous groups of UAVs based on a two-stage procedure for distributing agents of different specializations among task clusters, taking into account the agent's value function. At the first stage, the base part of the agents is distributed, the remaining agents at the second stage distributed in order to average the distance traveled by each agent. Execution of tasks within a cluster implemented by simulating annealing. To evaluate the effectiveness of the method variants, a comparison made with the greedy task distribution algorithm and the collective goal distribution algorithm. The analogs under consideration are widespread, universal and have a high convergence of the solution. Experimental studies car-ried out by computer simulation, where 2000 experiments carried out with various changes in the number of group agents and generation of a task map. The results showed the high efficiency of the task distribution method in terms of reducing the distance traveled by the agents of the UAV group when performing tasks in comparison with analogues. The efficiency of the path traveled by agents is up to 28% depending on the number of agents and tasks in the cluster, which is a scientific increment of the result of the study.

  • Open Access

    Method and algorithm for task allocation in a heterogeneous group of UAVs in a clustered field of targets

    by Vyacheslav Petrenko, Fariza Tebueva, Vladimir Antonov, Sergey Ryabtsev, Andrey Pavlov, Artur Sakolchik


  • Система распределения и планирования выполнения задач агентами роевых робототехнических систем на основе коллективного принятия решения

    by Вячеслав Иванович Петренко, Фариза Биляловна Тебуева, Андрей Сергеевич Павлов, Сергей Сергеевич Рябцев, Михаил Михайлович Гурчинский

    Внедрение логистических роботов в автоматизированные склады обеспечивает значительное повышение качества и сокращение затрат на логистику. В последнее время все большее внимание уделяется децентрализации управления логистическими роботами, что обеспечивает гибкость, надежность и масштабируемость системы. Исходя из этого логистические роботы, функционирующие в автоматизированном складе, часто рассматриваются как роевые робототехнические системы (РРТС). Известные методы распределения и планирования выполнения задач, используемые в составе программно-алгоритмического обеспечения централизованных систем управления логистических роботов, не учитывают ограничения сенсорных и вычислительных возможностей робототехнических устройств, используемых в составе РРТС (например, малый объем оперативной памяти, низкая тактовая частота процессора, малая емкость аккумуляторной батареи, низкая производительность бортовых датчиков и сенсоров и т. д.). Этот факт свидетельствует об отсутствии комплексного решения, позволяющего реализовать децентрализованную систему распределения и планирования выполнения задач логистическими роботами как роевую робототехническую систему. Таким образом, настоящая работа направлена на разработку подхода к синтезу децентрализованной системы распределения и планирования выполнения задач агентами роевых робототехнических систем при функционировании в автоматизированном складе. Отличительной особенностью предложенного подхода является использование процедуры коллективного принятия решения при распределении задач между агентами, что обеспечивает отсутствие коллизий (выбор одной и той же задачи двумя и более агентами). Элементом научной новизны в рамках предложенного подхода является метод коллективного принятия решений, отличающийся модифицированной процедурой выбора наилучшей альтернативы в соответствии с особенностями процесса распределения задач в роевых робототехнических системах. Достоверность полученных результатов подтверждена в ходе имитационного моделирования с использованием симулятора мультиагентных робототехнических систем ARGoS. Представленный подход к синтезу системы распределения и планирования выполнения задач на основе коллективного принятия решения может быть использован при моделировании децентрализованных систем управления роевых робототехнических систем.

  • Open Access

    Algorithm for monitoring the dynamic zone of forest fires by a group of unmanned aircraft

    by F. B. Tebueva, V. O. Antonov, M. Yu. Kabinyakov, N. Yu. Svistunov, М. Ю. Кабиняков

    Objective. The aim of the study is to develop an algorithm for monitoring forest fire zones, carried out by unmanned aerial vehicles (UAVs).Method. The study is based on methods of algorithmic support, methods of analysis and synthesis of automated control systems for technological objects.Result. The technologies and methods for monitoring forest fires are considered, which confirms the relevance of the use of UAVs to perform these tasks. An algorithm for the use of UAV swarms for monitoring forest fire zones is presented. The algorithm includes enlarged stages of decomposition of the global problem, distribution of tasks, application of methods of collective decision-making, etc.Conclusion. The proposed algorithm can be implemented subject to the development of swarm control theory.