Inna Khavina
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Inna Khavina has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Oleksandr Mozhaiev
Kharkiv National University of Internal Affairs
5 shared publications - Mikhail Tsuranov
Kharkiv National University of Internal Affairs
4 shared publications - Yurii Gnusov
Kharkiv National University of Internal Affairs
4 shared publications - Mykhailo Mozhaiev
Kharkiv National University of Radioelectronics
3 shared publications - Yurii Onishchenko
Kharkiv National University of Internal Affairs
2 shared publications - Anatolii Timoshyn
Харківський національний університет внутрішніх справ
1 shared publication
Latest Publications
- Open Access
- 22 October 2026
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 5 (4 (143)) , 46-57
Devising a method for dynamic load redistribution among SDN controllers in the fog layer of a mobile high-density internet of things
This study investigates the process that manages load on software-defined networks (SDN) controllers in the fog layer of the mobile high-density Internet of Things. The work considers SDN core controllers that handle OpenFlow switches located on mobile fog devices. The task addressed is to improve the efficiency of the ecosystem by reducing the load imbalance in SDN controllers and network latency. The integration of software-defined networks allows for flexible centralized traffic management, but SDN controllers become a bottleneck and are subject to load imbalance. This study proposes an architecture for the mobile high-density Internet of Things ecosystem focused on the use of SDN controllers in the fog layer. A feature of the architecture is a three-level hierarchical principle of building the SDN core. Based on this architecture, a mathematical model of the process of dynamic load balancing between SDN controllers was built. The model has made it possible to formalize the requirements for objective functions when optimizing the load balance of SDN controllers and minimizing network latency. The use of the model enabled devising a method for dynamic load redistribution on SDN core controllers. The main difference of the method is the use of a modified dung beetle optimization (DBO) algorithm with dynamic adjustment of the fitness function weights. The application of the DBO algorithm has made it possible to reduce the load dispersion in controllers by up to 30% compared to the classical genetic algorithm. The final solution is generated approximately 40% faster while the average query processing delay is reduced by 20%
- 22 October 2026
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 5 (4 (143)) , 46-57
Open AccessDevising a method for dynamic load redistribution among SDN controllers in the fog layer of a mobile high-density internet of things
This study investigates the process that manages load on software-defined networks (SDN) controllers in the fog layer of the mobile high-density Internet of Things. The work considers SDN core controllers that handle OpenFlow switches located on mobile fog devices. The task addressed is to improve the efficiency of the ecosystem by reducing the load imbalance in SDN controllers and network latency. The integration of software-defined networks allows for flexible centralized traffic management, but SDN controllers become a bottleneck and are subject to load imbalance. This study proposes an architecture for the mobile high-density Internet of Things ecosystem focused on the use of SDN controllers in the fog layer. A feature of the architecture is a three-level hierarchical principle of building the SDN core. Based on this architecture, a mathematical model of the process of dynamic load balancing between SDN controllers was built. The model has made it possible to formalize the requirements for objective functions when optimizing the load balance of SDN controllers and minimizing network latency. The use of the model enabled devising a method for dynamic load redistribution on SDN core controllers. The main difference of the method is the use of a modified dung beetle optimization (DBO) algorithm with dynamic adjustment of the fitness function weights. The application of the DBO algorithm has made it possible to reduce the load dispersion in controllers by up to 30% compared to the classical genetic algorithm. The final solution is generated approximately 40% faster while the average query processing delay is reduced by 20%
- Open Access
- 28 August 2026
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 4 (9 (142)) , 33-46
Design of a hybrid information security management system based on artificial intelligence technologies
The process of managing cybersecurity operations that include continuous monitoring, detection, analysis, and response to cyber threats, aimed at protecting the organization's digital assets, has been investigated in this study. The task addressed is to improve the efficiency and speed of automated incident response by combining deterministic pre-filtering tools with the cognitive capabilities of language models (LLMs). In the course of the research, an architecture of a multi-agent information security management system (MAS-ISM) has been designed, which operates on the basis of decentralized coalition auctions and a hybrid risk analysis subsystem (Sandwich Engine) for express search of incidents in system event logs for automated generation of expert reports in the state language using the generation technology supplemented by Retrieval-Augmented Generation (RAG) and LLM search. The solution to the tasks of obtaining technical cybersecurity reports in the state language and recommendations for further decision-making by the analyst has been shown. The main difference of the hybrid risk assessment system from existing ones is the use of deterministic retrospective session isolation, which made it possible to ensure data confidentiality, automatic expert description of the current state of cybersecurity in the national language, and the compilation of recommendations for analysts. The research results are attributed to the combined use of AI methods: RAG technology, deterministic retrospective session isolation, and LLM. The total time for analyzing one complex incident and forming a structured expert SOC report in the state language was reduced to 12 seconds (compared to 15–45 minutes under traditional manual analysis), while guaranteeing the confidentiality of critical data from leakage into the public cloud circuit
- 28 August 2026
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 4 (9 (142)) , 33-46
Open AccessDesign of a hybrid information security management system based on artificial intelligence technologies
The process of managing cybersecurity operations that include continuous monitoring, detection, analysis, and response to cyber threats, aimed at protecting the organization's digital assets, has been investigated in this study. The task addressed is to improve the efficiency and speed of automated incident response by combining deterministic pre-filtering tools with the cognitive capabilities of language models (LLMs). In the course of the research, an architecture of a multi-agent information security management system (MAS-ISM) has been designed, which operates on the basis of decentralized coalition auctions and a hybrid risk analysis subsystem (Sandwich Engine) for express search of incidents in system event logs for automated generation of expert reports in the state language using the generation technology supplemented by Retrieval-Augmented Generation (RAG) and LLM search. The solution to the tasks of obtaining technical cybersecurity reports in the state language and recommendations for further decision-making by the analyst has been shown. The main difference of the hybrid risk assessment system from existing ones is the use of deterministic retrospective session isolation, which made it possible to ensure data confidentiality, automatic expert description of the current state of cybersecurity in the national language, and the compilation of recommendations for analysts. The research results are attributed to the combined use of AI methods: RAG technology, deterministic retrospective session isolation, and LLM. The total time for analyzing one complex incident and forming a structured expert SOC report in the state language was reduced to 12 seconds (compared to 15–45 minutes under traditional manual analysis), while guaranteeing the confidentiality of critical data from leakage into the public cloud circuit
- 23 June 2026
- Published by International Science Group
INTELLIGENT DECISION SUPPORT SYSTEMS IN CYBERSECURITY: FROM FUZZY LOGIC TO LLM AGENTS
The monograph presents a holistic scientific concept of intelligent cybersecurity management at the enterprise level. The mathematical apparatus of hierarchical structuring of security parameters and strategic selection of protection systems using the analysis of hierarchies (AHI) method by T. Saati is highlighted. The development of decision support systems (DSS) based on the Mamdani fuzzy inference algorithm in the MATLAB environment is described in detail. Decentralized multi-agent systems built on the basis of the cooperative problem solving (CPS) model and optimized by auction algorithms for task distribution based on the “regret” criterion are considered. Special attention is paid to the integration of autonomous artificial intelligence agents and the development of corporate search-augmented generation (Agentic RAG) systems for proactive detection of zero-day threats and anomalous user behavior. The publication is intended for scientists, cybersecurity and information protection specialists, developers of intelligent systems, as well as graduate students and senior students in relevant specialties.
- 23 June 2026
- Published by International Science Group
INTELLIGENT DECISION SUPPORT SYSTEMS IN CYBERSECURITY: FROM FUZZY LOGIC TO LLM AGENTS
The monograph presents a holistic scientific concept of intelligent cybersecurity management at the enterprise level. The mathematical apparatus of hierarchical structuring of security parameters and strategic selection of protection systems using the analysis of hierarchies (AHI) method by T. Saati is highlighted. The development of decision support systems (DSS) based on the Mamdani fuzzy inference algorithm in the MATLAB environment is described in detail. Decentralized multi-agent systems built on the basis of the cooperative problem solving (CPS) model and optimized by auction algorithms for task distribution based on the “regret” criterion are considered. Special attention is paid to the integration of autonomous artificial intelligence agents and the development of corporate search-augmented generation (Agentic RAG) systems for proactive detection of zero-day threats and anomalous user behavior. The publication is intended for scientists, cybersecurity and information protection specialists, developers of intelligent systems, as well as graduate students and senior students in relevant specialties.
- Open Access
- 25 September 2025
- Published by Kharkiv National University of Radioelectronics in Innovative technologies and scientific solutions for industries
- No. 3(33),p. 166-179
Integrated information security risk management model based on ahp and bayesian networks
The subject of the study is information security risk management in a modern digital environment, where the integration of strategic and tactical approaches is necessary to ensure adaptive protection. The purpose of the work is to develop a hybrid model of cyber risk management by combining methodological analysis, expert assessments, probabilistic modeling and technical monitoring. The objectives of the study are: (1) analysis of the complementarity of the CRAMM methodology and SIEM systems; (2) construction of a procedure for quantitative prioritization of threats and vulnerabilities based on the analytical hierarchy process (AHP); (3) integration of the obtained estimates into Bayesian networks (BN) for probabilistic risk forecasting; (4) implementation of the proposed approach using modern automation tools. The methods used in the work include: CRAMM methodology for identifying assets, threats and vulnerabilities; Thomas Saati's AHP for quantitative assessment of priorities based on expert judgments with measurement of consistency using the Kendall concordance coefficient; mathematical modeling of causal relationships using Bayesian networks (BN); and the use of SIEM-class systems for operational monitoring of security events. The practical implementation of the approach was carried out using Python, in particular the Numpy, SciPy, pgmpy libraries, and the Streamlit web interface. Results. An integrated approach was developed that combines CRAMM, AHP, BN, and SIEM into a single adaptive risk management system. It is shown that AHP allows you to transform subjective expert assessments into objective weighting factors, which increases the reliability of the analysis. Based on these data, a Bayesian network was built to assess the risk of financial losses, which takes into account the presence of a threat, vulnerability, and a possible incident. The model is implemented programmatically, demonstrating the process of factoring the joint distribution and marginalizing latent variables to obtain posterior probabilities. The web interface based on Streamlit ensures the ease of use of the tool by non-professional users. Conclusions. The proposed hybrid approach allows for the effective combination of strategic planning (CRAMM), expert assessments (AHP), probabilistic modeling (BN) and operational monitoring (SIEM), forming a proactive, scientifically sound risk management system. Such integration provides a high level of adaptability and accuracy in a dynamic threat landscape, which makes the model practically applicable for organizations of various levels.
- 25 September 2025
- Published by Kharkiv National University of Radioelectronics in Innovative technologies and scientific solutions for industries
- No. 3(33),p. 166-179
Open AccessIntegrated information security risk management model based on ahp and bayesian networks
The subject of the study is information security risk management in a modern digital environment, where the integration of strategic and tactical approaches is necessary to ensure adaptive protection. The purpose of the work is to develop a hybrid model of cyber risk management by combining methodological analysis, expert assessments, probabilistic modeling and technical monitoring. The objectives of the study are: (1) analysis of the complementarity of the CRAMM methodology and SIEM systems; (2) construction of a procedure for quantitative prioritization of threats and vulnerabilities based on the analytical hierarchy process (AHP); (3) integration of the obtained estimates into Bayesian networks (BN) for probabilistic risk forecasting; (4) implementation of the proposed approach using modern automation tools. The methods used in the work include: CRAMM methodology for identifying assets, threats and vulnerabilities; Thomas Saati's AHP for quantitative assessment of priorities based on expert judgments with measurement of consistency using the Kendall concordance coefficient; mathematical modeling of causal relationships using Bayesian networks (BN); and the use of SIEM-class systems for operational monitoring of security events. The practical implementation of the approach was carried out using Python, in particular the Numpy, SciPy, pgmpy libraries, and the Streamlit web interface. Results. An integrated approach was developed that combines CRAMM, AHP, BN, and SIEM into a single adaptive risk management system. It is shown that AHP allows you to transform subjective expert assessments into objective weighting factors, which increases the reliability of the analysis. Based on these data, a Bayesian network was built to assess the risk of financial losses, which takes into account the presence of a threat, vulnerability, and a possible incident. The model is implemented programmatically, demonstrating the process of factoring the joint distribution and marginalizing latent variables to obtain posterior probabilities. The web interface based on Streamlit ensures the ease of use of the tool by non-professional users. Conclusions. The proposed hybrid approach allows for the effective combination of strategic planning (CRAMM), expert assessments (AHP), probabilistic modeling (BN) and operational monitoring (SIEM), forming a proactive, scientifically sound risk management system. Such integration provides a high level of adaptability and accuracy in a dynamic threat landscape, which makes the model practically applicable for organizations of various levels.
- Open Access
- 28 June 2024
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 3 (3 (129)) , 6-15
Design of a decision support system to form optimal technological processes for parts machining based on artificial intelligence methods
The object of this study is the process of designing a decision support system for automating the formation of technological processes (TPs) for machining parts of high-precision equipment for the aviation industry. The task of improving the efficiency of the optimization of the process of mechanical processing of parts through the use of a decision support system (DSS) and artificial intelligence methods, which, unlike known analytical approaches, allow describing processes and phenomena that do not have strict formalization, has been solved. DSS consists of three subsystems. The first is an information subsystem for the automated formation of the structure in the technological process of machining parts of high-precision equipment. The second is an information subsystem for optimizing parameters of TP operations by cutting, taking into account the accumulation of tool wear. The third is a subsystem of control and adjustment of operating parameters. In the process of conducting research, an approach was devised for designing optimal technological processes to machine parts of high-precision equipment. The task of designing the structure of technological processes was solved using production rules. The task of determining the optimal parameters of turning and milling operations was solved in a multi-criteria statement. The following objective functions were used: cost of the operation, specific energy consumption for the operation, and productivity of the operation. At the same time, the wear of the tool accumulated over time was taken into account. The solution was obtained by searching for the Pareto-optimal solution using genetic algorithms and artificial neural networks. As a result of the work of DSS, an optimal technological process for machining parts of high-precision equipment for the aviation industry was formed, which made it possible to reduce the production time of one part by 5 % and reduce the total cost of production of the part by 14 %
- 28 June 2024
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 3 (3 (129)) , 6-15
Open AccessDesign of a decision support system to form optimal technological processes for parts machining based on artificial intelligence methods
The object of this study is the process of designing a decision support system for automating the formation of technological processes (TPs) for machining parts of high-precision equipment for the aviation industry. The task of improving the efficiency of the optimization of the process of mechanical processing of parts through the use of a decision support system (DSS) and artificial intelligence methods, which, unlike known analytical approaches, allow describing processes and phenomena that do not have strict formalization, has been solved. DSS consists of three subsystems. The first is an information subsystem for the automated formation of the structure in the technological process of machining parts of high-precision equipment. The second is an information subsystem for optimizing parameters of TP operations by cutting, taking into account the accumulation of tool wear. The third is a subsystem of control and adjustment of operating parameters. In the process of conducting research, an approach was devised for designing optimal technological processes to machine parts of high-precision equipment. The task of designing the structure of technological processes was solved using production rules. The task of determining the optimal parameters of turning and milling operations was solved in a multi-criteria statement. The following objective functions were used: cost of the operation, specific energy consumption for the operation, and productivity of the operation. At the same time, the wear of the tool accumulated over time was taken into account. The solution was obtained by searching for the Pareto-optimal solution using genetic algorithms and artificial neural networks. As a result of the work of DSS, an optimal technological process for machining parts of high-precision equipment for the aviation industry was formed, which made it possible to reduce the production time of one part by 5 % and reduce the total cost of production of the part by 14 %
- Open Access
- 3 November 2023
- Published by National Technical University Kharkiv Polytechnic Institute in Bulletin of the National technical university "Kharkiv Polytechnic Institute" Series: Techniques in a machine industry
- No. 2(8),p. 65-77
STATIC DEFORMATION ANALYSIS OF A MOBILE CUTTING MACHINE
Проведено аналіз спеціальних вимог та критеріїв, що висуваються до мобільних верстатів. На базі відомих підходів до статичних розрахунків шпиндельних вузлів запропоновані розрахункові схеми та математична модель для статичного аналізу шпиндельного валу на нелінійних опорах. У запропонованому підході використовується модель балки Тимошенко. Рішення диференційного рівняння зігнутої осі балки здійснюється методом початкових параметрів у матричній формі. Нелінійна система рівнянь формується автоматично для конкретної розрахункової схеми. Для її рішення застосовується метод простих послідовних ітерацій. Особливістю роботи є врахування нелінійной залежності деформації підшипників від діючих на них навантажень. У якості прикладу проведено статичний аналіз шпиндельного валу мобільной розточувальної машини ХТ7809-0524, призначеної для розточування отворів великого діаметру. Для декількох варіантів розрахункових схем проведена оцінка згинальної жорсткості, розрахунок прогинів та кутів повороту у робочому режимі. Побудовані графіки розподілу переміщень перерізів шпиндельного валу вздовж його осі. З’ясовано що лінійна жорсткість шпиндельного вала розточувальної машини ХТ7809-0524 нижче нормативної, принятої у верстатобудуванні. Приведено графіки розподілу внутрішніх зусиль у перерізах шпиндельного валу, зроблено оцінку його міцності. Встановлено, що рівень максимальних напружень на робочому режимі є прийнятним і достатнім для забезпечення необхідного запасу міцності вала.
- 3 November 2023
- Published by National Technical University Kharkiv Polytechnic Institute in Bulletin of the National technical university "Kharkiv Polytechnic Institute" Series: Techniques in a machine industry
- No. 2(8),p. 65-77
Open AccessSTATIC DEFORMATION ANALYSIS OF A MOBILE CUTTING MACHINE
Проведено аналіз спеціальних вимог та критеріїв, що висуваються до мобільних верстатів. На базі відомих підходів до статичних розрахунків шпиндельних вузлів запропоновані розрахункові схеми та математична модель для статичного аналізу шпиндельного валу на нелінійних опорах. У запропонованому підході використовується модель балки Тимошенко. Рішення диференційного рівняння зігнутої осі балки здійснюється методом початкових параметрів у матричній формі. Нелінійна система рівнянь формується автоматично для конкретної розрахункової схеми. Для її рішення застосовується метод простих послідовних ітерацій. Особливістю роботи є врахування нелінійной залежності деформації підшипників від діючих на них навантажень. У якості прикладу проведено статичний аналіз шпиндельного валу мобільной розточувальної машини ХТ7809-0524, призначеної для розточування отворів великого діаметру. Для декількох варіантів розрахункових схем проведена оцінка згинальної жорсткості, розрахунок прогинів та кутів повороту у робочому режимі. Побудовані графіки розподілу переміщень перерізів шпиндельного валу вздовж його осі. З’ясовано що лінійна жорсткість шпиндельного вала розточувальної машини ХТ7809-0524 нижче нормативної, принятої у верстатобудуванні. Приведено графіки розподілу внутрішніх зусиль у перерізах шпиндельного валу, зроблено оцінку його міцності. Встановлено, що рівень максимальних напружень на робочому режимі є прийнятним і достатнім для забезпечення необхідного запасу міцності вала.
- Open Access
- 21 December 2022
- Published by Kharkiv National University of Internal Affairs in Law and Safety
- Vol. 87 (4) , 171-183
Development of multi-agent information security management system
The issue of creating an information security system is very relevant in the world today. One of the urgent tasks is to solve the issues of effective protection of information from both external and internal threats through the creation and implementation of information security management systems in automated systems of enterprises, which, among other things, requires the formalization of the task of protecting information for its subsequent implementation by software and other means. Now there are security analysis systems, for example, that examine the security elements settings of workstations and servers operating systems, analyze the network topology, look for unprotected network connections, examine the settings of firewalls. The disadvantage of these systems is that they are not suitable for monitoring large volumes of network traffic. The solution to this problem is the use of monitoring tools capable of analyzing large amounts of data in real time. Therefore, a significant place in the article is given to the review of developments based on artificial intelligence technologies, namely multi-agent systems, review of information security models, threat risk assessment in automated systems. The functional architecture of the information security management system based on a multi-agent system has been proposed to search in real time for information security optimal solutions through the selection of such coalitions of protection mechanisms agents that will allow to build the optimal protection of the automated system according to the selected criteria. The model with complete overlapping of threats has been substantiated and adopted as a basis, which allows to analyze the overall situation and choose strategically important decisions directly during the organization of information security. The essence of of multi-agent systems functioning that implement a decentralized control system based on the work of autonomous agents that can be implemented programmatically has been revealed. The role of threat agents, resource agents, agents of protection mechanisms and their functional purpose have been defined. The problem of searching a set of protection mechanisms agents coalition for the current state of the automated system as a problem of optimal search by the criterion of protection cost, taking into account the value of information, has been generalized. Due to the modularity of the multi-agent system, the further work will be aimed at detailing its components and perfection.
- 21 December 2022
- Published by Kharkiv National University of Internal Affairs in Law and Safety
- Vol. 87 (4) , 171-183
Open AccessDevelopment of multi-agent information security management system
The issue of creating an information security system is very relevant in the world today. One of the urgent tasks is to solve the issues of effective protection of information from both external and internal threats through the creation and implementation of information security management systems in automated systems of enterprises, which, among other things, requires the formalization of the task of protecting information for its subsequent implementation by software and other means. Now there are security analysis systems, for example, that examine the security elements settings of workstations and servers operating systems, analyze the network topology, look for unprotected network connections, examine the settings of firewalls. The disadvantage of these systems is that they are not suitable for monitoring large volumes of network traffic. The solution to this problem is the use of monitoring tools capable of analyzing large amounts of data in real time. Therefore, a significant place in the article is given to the review of developments based on artificial intelligence technologies, namely multi-agent systems, review of information security models, threat risk assessment in automated systems. The functional architecture of the information security management system based on a multi-agent system has been proposed to search in real time for information security optimal solutions through the selection of such coalitions of protection mechanisms agents that will allow to build the optimal protection of the automated system according to the selected criteria. The model with complete overlapping of threats has been substantiated and adopted as a basis, which allows to analyze the overall situation and choose strategically important decisions directly during the organization of information security. The essence of of multi-agent systems functioning that implement a decentralized control system based on the work of autonomous agents that can be implemented programmatically has been revealed. The role of threat agents, resource agents, agents of protection mechanisms and their functional purpose have been defined. The problem of searching a set of protection mechanisms agents coalition for the current state of the automated system as a problem of optimal search by the criterion of protection cost, taking into account the value of information, has been generalized. Due to the modularity of the multi-agent system, the further work will be aimed at detailing its components and perfection.