Nataliia Kozirova
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Nataliia Kozirova has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Oleksii Smirnov
Central Ukrainian National Technical University
5 shared publications - Oksana Konoplitska-Slobodeniuk
Central Ukrainian National Technical University
4 shared publications - Liliia Konstantynova
Central Ukrainian National Technical University
3 shared publications - Oksana Kravchuk
Central Ukrainian National Technical University
3 shared publications Олексій Смірнов
Центральноукраїнський національний технічний університет
3 shared publications- Kostiantyn Buravchenko
Central Ukrainian National Technical University
2 shared publications
Latest Publications
- Open Access
- 25 June 2026
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 1 (33) , 667-682
RESEARCH INTO THE APPLICATION OF VECTOR DATABASES IN GENERATIVE ARTIFICIAL INTELLIGENCE
This paper studies the use of vector databases in generative artificial intelligence. The purpose of this article is to study the possibility of using vector databases as the foundation of modern AI infrastructure and their role in expanding the cognitive capabilities of GenAI. The object of the study is the process of using databases in artificial intelligence. The subject of the study is the use of vector databases in generative artificial intelligence. The following tasks were solved in this study: the role of vector repositories in expanding the cognitive capabilities of generative AI was investigated; a comparative analysis of traditional relational systems and vector databases was carried out; the mechanics and verification potential of the RAG and RAFT architectural paradigms were analyzed. Prospects for further research are identified, which consist of the following: development of effective mechanisms for monitoring and automatic correction of semantic drift of embeddings in conditions of constant updating of corporate knowledge; research into adaptive memory management strategies to eliminate threshold performance effects when scaling vector indexes; research into the possibilities of combining hybrid search architectures that combine semantic and full-text indexing in a single technological environment; standardization of metrics for assessing the quality of vector search in the context of specific requirements of industrial RAG systems, which will ensure a more informed choice of infrastructure solutions for specific application tasks.
- 25 June 2026
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 1 (33) , 667-682
Open AccessRESEARCH INTO THE APPLICATION OF VECTOR DATABASES IN GENERATIVE ARTIFICIAL INTELLIGENCE
This paper studies the use of vector databases in generative artificial intelligence. The purpose of this article is to study the possibility of using vector databases as the foundation of modern AI infrastructure and their role in expanding the cognitive capabilities of GenAI. The object of the study is the process of using databases in artificial intelligence. The subject of the study is the use of vector databases in generative artificial intelligence. The following tasks were solved in this study: the role of vector repositories in expanding the cognitive capabilities of generative AI was investigated; a comparative analysis of traditional relational systems and vector databases was carried out; the mechanics and verification potential of the RAG and RAFT architectural paradigms were analyzed. Prospects for further research are identified, which consist of the following: development of effective mechanisms for monitoring and automatic correction of semantic drift of embeddings in conditions of constant updating of corporate knowledge; research into adaptive memory management strategies to eliminate threshold performance effects when scaling vector indexes; research into the possibilities of combining hybrid search architectures that combine semantic and full-text indexing in a single technological environment; standardization of metrics for assessing the quality of vector search in the context of specific requirements of industrial RAG systems, which will ensure a more informed choice of infrastructure solutions for specific application tasks.
- 1 January 2025
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 3 (27) , 429-448
RESEARCH OF ARTIFICIAL INTELLIGENCE TOOLS FOR WORKING WITH DATABASES AND DATA ANALYSIS
This paper examines artificial intelligence tools for working with databases and data analysis. The purpose of this paper is to investigate the means and possibilities of using artificial intelligence in solving problems that arise when working with databases. The object of the study is the process of applying artificial intelligence. The subject of the study is the definition of artificial intelligence tools for working with databases and data analysis. The following tasks were solved in this study: the integration of artificial intelligence into databases was investigated; artificial intelligence tools for database design were analyzed; artificial intelligence tools for data analysis were analyzed; ways of using Generative AI for databases were considered. Each of the tools considered represents solutions based on artificial intelligence, has unique functions and strengths, and is capable of solving a variety of tasks. As artificial intelligence continues to develop, these tools will undoubtedly become an even more integral part of the success of organizations managing data.
- 1 January 2025
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 3 (27) , 429-448
RESEARCH OF ARTIFICIAL INTELLIGENCE TOOLS FOR WORKING WITH DATABASES AND DATA ANALYSIS
This paper examines artificial intelligence tools for working with databases and data analysis. The purpose of this paper is to investigate the means and possibilities of using artificial intelligence in solving problems that arise when working with databases. The object of the study is the process of applying artificial intelligence. The subject of the study is the definition of artificial intelligence tools for working with databases and data analysis. The following tasks were solved in this study: the integration of artificial intelligence into databases was investigated; artificial intelligence tools for database design were analyzed; artificial intelligence tools for data analysis were analyzed; ways of using Generative AI for databases were considered. Each of the tools considered represents solutions based on artificial intelligence, has unique functions and strengths, and is capable of solving a variety of tasks. As artificial intelligence continues to develop, these tools will undoubtedly become an even more integral part of the success of organizations managing data.
- Open Access
- 1 January 2024
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 1 (25) , 6-18
STUDY OF THE CURRENT STATE OF SIEM SYSTEMS
In this work, a study of SIEM systems, the relevance of which has grown significantly during the full-scale invasion of Russia into Ukraine, has been carried out. The task of finding the most optimal solutions was solved according to the following criteria: ease of use, ability to integrate with other protection solutions, pricing policy and features. For this purpose, the work considered a general description of the structure and principle of operation of the SIEM system, determined the capabilities and features of modern SIEM systems, conducted a study of the following software (software): Splunk Enterprise Security (Splunk), Elastic Security, IBM QRadar SIEM, Wazuh SIEM, Microsoft Sentinel. As a result of the research, the following was revealed: modern SIEM solutions allow automating part of the processes of detection and response to security events, allow to take control of hybrid types of infrastructure, which may include cloud environments, virtualization and containerization systems, workstations and other corporate devices. They are implemented both in the form of deployment of their solutions at their own facilities, and in the form of renting relevant resources, providing a Software-as-a-Service service. At the same time, the presence of a large number of integrations with various software packages and systems allows SIEM to monitor the compliance of the current state of cyber protection of the organization's information infrastructure with certain international standards, such as ISO 27001, GDPR or PCI DSS. It was determined that modern SIEMs use advances in machine learning and artificial intelligence to detect anomalies in system and user behavior, as well as to prioritize identified vulnerabilities and suggest steps to improve the state of cyber defense. The considered solutions work in conjunction with other modern systems, such as SOAR or EDR/XDR, which increases the efficiency of SIEM systems and, as a result, security operation centers, therefore, according to the authors, the corresponding technologies deserve further research.
- 1 January 2024
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 1 (25) , 6-18
Open AccessSTUDY OF THE CURRENT STATE OF SIEM SYSTEMS
In this work, a study of SIEM systems, the relevance of which has grown significantly during the full-scale invasion of Russia into Ukraine, has been carried out. The task of finding the most optimal solutions was solved according to the following criteria: ease of use, ability to integrate with other protection solutions, pricing policy and features. For this purpose, the work considered a general description of the structure and principle of operation of the SIEM system, determined the capabilities and features of modern SIEM systems, conducted a study of the following software (software): Splunk Enterprise Security (Splunk), Elastic Security, IBM QRadar SIEM, Wazuh SIEM, Microsoft Sentinel. As a result of the research, the following was revealed: modern SIEM solutions allow automating part of the processes of detection and response to security events, allow to take control of hybrid types of infrastructure, which may include cloud environments, virtualization and containerization systems, workstations and other corporate devices. They are implemented both in the form of deployment of their solutions at their own facilities, and in the form of renting relevant resources, providing a Software-as-a-Service service. At the same time, the presence of a large number of integrations with various software packages and systems allows SIEM to monitor the compliance of the current state of cyber protection of the organization's information infrastructure with certain international standards, such as ISO 27001, GDPR or PCI DSS. It was determined that modern SIEMs use advances in machine learning and artificial intelligence to detect anomalies in system and user behavior, as well as to prioritize identified vulnerabilities and suggest steps to improve the state of cyber defense. The considered solutions work in conjunction with other modern systems, such as SOAR or EDR/XDR, which increases the efficiency of SIEM systems and, as a result, security operation centers, therefore, according to the authors, the corresponding technologies deserve further research.
- Open Access
- 1 January 2024
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 4 (24) , 6-27
RESEARCH OF CYBER SECURITY TECHNOLOGIES OF CLOUD SERVICES IAAS, PAAS AND SAAS
Cybersecurity threats are constantly evolving, and cloud computing is no exception. Attackers are improving attack techniques aimed at identifying vulnerabilities in IaaS, PaaS, and SaaS. The work examines the following problematic issues: insufficient analytical tools; data privacy and security; financial and organizational costs to ensure cyber security of IaaS, PaaS and SaaS cloud technologies. The aim of the work is to investigate how the common models of cloud computing: infrastructure as a service (IaaS), platform as a service (PaaS) and software as a service (SaaS) need to properly implement adequate and appropriate protection measures to ensure cyber security. For this purpose, the paper examined models of cloud technologies, it was determined that cloud services include various models that allow users to access various types of resources via the Internet. It has been found that there are three generally accepted models of cloud services: infrastructure as a service (IaaS), platform as a service (PaaS) and software as a service (SaaS), and two main players: the cloud provider and the cloud subscriber. The set of levels over which each of these players has control depends on the model of the cloud service or environment. For each of these cloud services, its description was given, recommendations were given for access control, privacy assurance, terms of use were defined, advantages and disadvantages were given, and market trends of these services were considered. Proposed approaches to the formation of a secure application development environment in cloud services. Features such as wide network access, resource pooling, fast elasticity, service metering, and data sharing are also summarized. Guidelines for designing access control for IaaS, PaaS, and SaaS according to their different characteristics are proposed. In addition, the security policy rules for each cloud system are summarized. Technologies are proposed to protect security at each of the three main layers of cloud services: the application, middleware, and virtual machine layers, due to differences in the organization that controls each of these layers. It was found that for any level it is possible to provide more effective protection if the same subject controls the level below. Since the network, hardware, and resource abstraction layer in all cloud service models are controlled by the cloud provider, it has more effective protections at its disposal.
- 1 January 2024
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 4 (24) , 6-27
Open AccessRESEARCH OF CYBER SECURITY TECHNOLOGIES OF CLOUD SERVICES IAAS, PAAS AND SAAS
Cybersecurity threats are constantly evolving, and cloud computing is no exception. Attackers are improving attack techniques aimed at identifying vulnerabilities in IaaS, PaaS, and SaaS. The work examines the following problematic issues: insufficient analytical tools; data privacy and security; financial and organizational costs to ensure cyber security of IaaS, PaaS and SaaS cloud technologies. The aim of the work is to investigate how the common models of cloud computing: infrastructure as a service (IaaS), platform as a service (PaaS) and software as a service (SaaS) need to properly implement adequate and appropriate protection measures to ensure cyber security. For this purpose, the paper examined models of cloud technologies, it was determined that cloud services include various models that allow users to access various types of resources via the Internet. It has been found that there are three generally accepted models of cloud services: infrastructure as a service (IaaS), platform as a service (PaaS) and software as a service (SaaS), and two main players: the cloud provider and the cloud subscriber. The set of levels over which each of these players has control depends on the model of the cloud service or environment. For each of these cloud services, its description was given, recommendations were given for access control, privacy assurance, terms of use were defined, advantages and disadvantages were given, and market trends of these services were considered. Proposed approaches to the formation of a secure application development environment in cloud services. Features such as wide network access, resource pooling, fast elasticity, service metering, and data sharing are also summarized. Guidelines for designing access control for IaaS, PaaS, and SaaS according to their different characteristics are proposed. In addition, the security policy rules for each cloud system are summarized. Technologies are proposed to protect security at each of the three main layers of cloud services: the application, middleware, and virtual machine layers, due to differences in the organization that controls each of these layers. It was found that for any level it is possible to provide more effective protection if the same subject controls the level below. Since the network, hardware, and resource abstraction layer in all cloud service models are controlled by the cloud provider, it has more effective protections at its disposal.
- Open Access
- 1 January 2024
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 3 (23) , 111-131
STUDY OF REQUIREMENTS AND CYBER SECURITY ANALYSIS OF THE SOFTWARE OF INFORMATION AND CONTROL SYSTEMS OF NPP, IMPORTANT FOR SECURITY
In order to counter cryptoattacks on elements of critical infrastructure, in particular on computer control systems of nuclear power plants, the goal achieved in this work is to analyze the requirements for computer security (cyber security) of the software of this system, which are relevant to the stage of its design, development and operation, as well as proposed criteria and methodology for calculating the quality of compliance with these requirements. To achieve the goal, the first section of the article provides information on standards and identified requirements for software cyber security. In the second section, an analysis of the requirements is carried out and an approach to software development is described, taking into account these requirements and analyzing their consideration. In the third section, an approach to calculating the performance indicator of software cyber security requirements is proposed. The fourth chapter provides an example of the application of this approach to the existing computerized NPP management system to assess compliance with cyber security requirements. The article discusses the requirements of the international standard IEC62645 and the industry standard of Ukraine “NP 306.2.237-2022”, which are related to the development of software for the computer control system of nuclear power plants. Ensuring cyber protection of the software of the NPP computer management system is a complex task that includes administrative, legal, technical, cultural, and organizational components. From the point of view of software development and operation, the main cyber security measures include software code verification, ensuring the absence of hidden functions, implementing physical equipment protection, security of software components, authentication, security during data exchange. To determine the compliance of the software with the requirements of cyber protection, it is necessary to determine the requirements applicable to each component of the software and conduct an analysis of their implementation. This action should occur continuously during the development of new software and software evaluation of existing computer control systems. After the analysis of the applicability and fulfillment of the requirements, the calculation of the coefficient of the fulfillment of the requirements can be carried out. It was noted that cyber protection is only a component of the quality of the software of the NPP computer control system, which is important for the performance of security functions. The analysis of requirements and the calculation of the coefficient of their fulfillment can be an integral part of the complex model of the software development process of the computer system of NPP management.
- 1 January 2024
- Published by Borys Grinchenko Kyiv University in Cybersecurity: Education, Science, Technique
- Vol. 3 (23) , 111-131
Open AccessSTUDY OF REQUIREMENTS AND CYBER SECURITY ANALYSIS OF THE SOFTWARE OF INFORMATION AND CONTROL SYSTEMS OF NPP, IMPORTANT FOR SECURITY
In order to counter cryptoattacks on elements of critical infrastructure, in particular on computer control systems of nuclear power plants, the goal achieved in this work is to analyze the requirements for computer security (cyber security) of the software of this system, which are relevant to the stage of its design, development and operation, as well as proposed criteria and methodology for calculating the quality of compliance with these requirements. To achieve the goal, the first section of the article provides information on standards and identified requirements for software cyber security. In the second section, an analysis of the requirements is carried out and an approach to software development is described, taking into account these requirements and analyzing their consideration. In the third section, an approach to calculating the performance indicator of software cyber security requirements is proposed. The fourth chapter provides an example of the application of this approach to the existing computerized NPP management system to assess compliance with cyber security requirements. The article discusses the requirements of the international standard IEC62645 and the industry standard of Ukraine “NP 306.2.237-2022”, which are related to the development of software for the computer control system of nuclear power plants. Ensuring cyber protection of the software of the NPP computer management system is a complex task that includes administrative, legal, technical, cultural, and organizational components. From the point of view of software development and operation, the main cyber security measures include software code verification, ensuring the absence of hidden functions, implementing physical equipment protection, security of software components, authentication, security during data exchange. To determine the compliance of the software with the requirements of cyber protection, it is necessary to determine the requirements applicable to each component of the software and conduct an analysis of their implementation. This action should occur continuously during the development of new software and software evaluation of existing computer control systems. After the analysis of the applicability and fulfillment of the requirements, the calculation of the coefficient of the fulfillment of the requirements can be carried out. It was noted that cyber protection is only a component of the quality of the software of the NPP computer control system, which is important for the performance of security functions. The analysis of requirements and the calculation of the coefficient of their fulfillment can be an integral part of the complex model of the software development process of the computer system of NPP management.