Ruslan Kozak - Academia.edu (original) (raw)
Papers by Ruslan Kozak
Challenges to national defence in contemporary geopolitical situation, Nov 3, 2022
This paper presents the result of the study of network intrusion detection using machine learning... more This paper presents the result of the study of network intrusion detection using machine learning algorithms. The creation and training of such algorithms is seriously limited by the small number of actual datasets available for public access. The CSE-CIC-IDS2018 data set, used in research, includes 7 subsets of different attack scenarios. Each subset is labeled using a few subtypes of a given attack or normal behavior. That is why the problem of network attack detection has been considered a multiclassification problem. Some of the most popular classifiers will be tested on the chosen data set. Classification algorithms are developed using a standard Python programming environment and the specialized machine learning library Scikit-learn. In the paper, a comparative analysis of the results was performed based on the the application of Random Forest, XGBoost, LR, and MLP classifiers.
Journal of physics, Mar 1, 2021
The use of augmented reality-enabled scenarios in cybersecurity teaching is proposed in the artic... more The use of augmented reality-enabled scenarios in cybersecurity teaching is proposed in the article to respond to new requirements for the rapid adoption of new technologies and profound knowledge of cybersecurity issues by professionals. Implementation of project-type activities based on real cybersecurity issues in application fields of cyber-physical systems is suggested to improve the competence forming. A use-case of agricultural cyber-physical system of systems is discussed as a viable example of augmented reality-enabled prototyping of cybersecurity risk-aware architecture. The necessary steps are analysis of general and business-specific tasks on cybersecurity, creation of a list of competencies, formalized in educational standards and curricula, development of gaming scenarios for the formation of hard and soft skills, development of the scenario management system for AR interfaces. The system using AR tools can be easily adapted to different cybersecurity training activities. Industrial cyber-physical systems may be vulnerable due to insecure wireless connectivity, lack of encryption, inadequate access policy. The project-based learning complex is focused on the implementation of a data acquisition, storage and processing platform for new sensor networks and instruments. Representing all the diverse information on different layers will be greatly improved by use of the developed holographic projection AR tools.
Review of main approaches of gas consumption prognosis and analysis models is given here. Most of... more Review of main approaches of gas consumption prognosis and analysis models is given here. Most of them are long-term prognosis methods, which take into account some weather conditions (mostly temperature as most significant one), few short-term methods works only for non-heating period. Unlike the existing methods, new approach gives a possibility to analyze and calculate prognosis values of gas consumption in heating season taking into consideration its cyclic nature and temperature of environment at the same time. It helps to monitor, analyze, plan and manage loading of gas system during the day.
Applied Sciences
The growing popularity of data outsourcing to third-party cloud servers has a downside, related t... more The growing popularity of data outsourcing to third-party cloud servers has a downside, related to the serious concerns of data owners about their security due to possible leakage. The desire to reduce the risk of loss of data confidentiality has become a motivating start to developing mechanisms that provide the ability to effectively use encryption to protect data. However, the use of traditional encryption methods faces a problem. Namely, traditional encryption, by making it impossible for insiders and outsiders to access data without knowing the keys, excludes the possibility of searching. This paper presents a solution that provides a strong level of confidentiality when searching, inserting, modifying, and deleting the required sensitive data in a remote database whose data are encrypted. The proposed SQL query processing technique allows the DBMS server to perform search functions over encrypted data in the same way as in an unencrypted database. This is achieved through the ...
Information
The problem of nonlinear substitution generation (S-boxes) is investigated in many related works ... more The problem of nonlinear substitution generation (S-boxes) is investigated in many related works in symmetric key cryptography. In particular, the strength of symmetric ciphers to linear cryptanalysis is directly related to the nonlinearity of substitution. In addition to being highly nonlinear, S-boxes must be random, i.e., must not contain hidden mathematical constructs that facilitate algebraic cryptanalysis. The generation of such substitutions is a complex combinatorial optimization problem. Probabilistic algorithms are used to solve it, for instance the simulated annealing algorithm, which is well-fitted to a discrete search space. We propose a new cost function based on Walsh–Hadamard spectrum computation, and investigate the search efficiency of S-boxes using a simulated annealing algorithm. For this purpose, we conduct numerous experiments with different input parameters: initial temperature, cooling coefficient, number of internal and external loops. As the results of the ...
Challenges to national defence in contemporary geopolitical situation, Nov 3, 2022
This paper presents the result of the study of network intrusion detection using machine learning... more This paper presents the result of the study of network intrusion detection using machine learning algorithms. The creation and training of such algorithms is seriously limited by the small number of actual datasets available for public access. The CSE-CIC-IDS2018 data set, used in research, includes 7 subsets of different attack scenarios. Each subset is labeled using a few subtypes of a given attack or normal behavior. That is why the problem of network attack detection has been considered a multiclassification problem. Some of the most popular classifiers will be tested on the chosen data set. Classification algorithms are developed using a standard Python programming environment and the specialized machine learning library Scikit-learn. In the paper, a comparative analysis of the results was performed based on the the application of Random Forest, XGBoost, LR, and MLP classifiers.
2017 9th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS), 2017
Intensive development of information systems has led to an increase in malicious software, which ... more Intensive development of information systems has led to an increase in malicious software, which is associated with the emergence of new types of cyber attacks. Expanding impact of cyber attacks aimed at a variety of resources information system initiates creation of special countermeasures that can be effective in the emergence of new types of threats from unknown or ill-defined properties. There are enough effective developments, are used to solve problems of cyber attacks identification, for example, the method of linguistic etalons formation for the detection of intrusion systems, which does not disclose the mechanism of the formation of etalons settings for sniffing attacks. In this work, was developed etalons model of linguistic variables to detect sniffing attacks, which is due to assess the state of the information system and the process of forming the parameters of etalons will allow to formalize the process of obtaining the parameters of etalons for a given linguistic variables in specific environment in solving attacks detection tasks on computer systems.
Information & Security: An International Journal, 2016
Leading companies in the field of ICT often provide training courses. Such courses are found attr... more Leading companies in the field of ICT often provide training courses. Such courses are found attractive by students, especially students specializing in technical disciplines. In this article, we review courses provided by Cisco Systems, describe their organization, nomenclature and structure, and provide recommendations on their use in the academic curricula in the field of information and communications security. The inclusion of such courses in the academic curricula is considered beneficial in terms of competitiveness of graduates on current and foreseen labour markets.
Review of main approaches of gas consumption prognosis and analysis models is given here. Most of... more Review of main approaches of gas consumption prognosis and analysis models is given here. Most of them are long-term prognosis methods, which take into account some weather conditions (mostly temperature as most significant one), few short-term methods works only for non-heating period. Unlike the existing methods, new approach gives a possibility to analyze and calculate prognosis values of gas consumption in heating season taking into consideration its cyclic nature and temperature of environment at the same time. It helps to monitor, analyze, plan and manage loading of gas system during the day.
Challenges to national defence in contemporary geopolitical situation, Nov 3, 2022
This paper presents the result of the study of network intrusion detection using machine learning... more This paper presents the result of the study of network intrusion detection using machine learning algorithms. The creation and training of such algorithms is seriously limited by the small number of actual datasets available for public access. The CSE-CIC-IDS2018 data set, used in research, includes 7 subsets of different attack scenarios. Each subset is labeled using a few subtypes of a given attack or normal behavior. That is why the problem of network attack detection has been considered a multiclassification problem. Some of the most popular classifiers will be tested on the chosen data set. Classification algorithms are developed using a standard Python programming environment and the specialized machine learning library Scikit-learn. In the paper, a comparative analysis of the results was performed based on the the application of Random Forest, XGBoost, LR, and MLP classifiers.
Journal of physics, Mar 1, 2021
The use of augmented reality-enabled scenarios in cybersecurity teaching is proposed in the artic... more The use of augmented reality-enabled scenarios in cybersecurity teaching is proposed in the article to respond to new requirements for the rapid adoption of new technologies and profound knowledge of cybersecurity issues by professionals. Implementation of project-type activities based on real cybersecurity issues in application fields of cyber-physical systems is suggested to improve the competence forming. A use-case of agricultural cyber-physical system of systems is discussed as a viable example of augmented reality-enabled prototyping of cybersecurity risk-aware architecture. The necessary steps are analysis of general and business-specific tasks on cybersecurity, creation of a list of competencies, formalized in educational standards and curricula, development of gaming scenarios for the formation of hard and soft skills, development of the scenario management system for AR interfaces. The system using AR tools can be easily adapted to different cybersecurity training activities. Industrial cyber-physical systems may be vulnerable due to insecure wireless connectivity, lack of encryption, inadequate access policy. The project-based learning complex is focused on the implementation of a data acquisition, storage and processing platform for new sensor networks and instruments. Representing all the diverse information on different layers will be greatly improved by use of the developed holographic projection AR tools.
Review of main approaches of gas consumption prognosis and analysis models is given here. Most of... more Review of main approaches of gas consumption prognosis and analysis models is given here. Most of them are long-term prognosis methods, which take into account some weather conditions (mostly temperature as most significant one), few short-term methods works only for non-heating period. Unlike the existing methods, new approach gives a possibility to analyze and calculate prognosis values of gas consumption in heating season taking into consideration its cyclic nature and temperature of environment at the same time. It helps to monitor, analyze, plan and manage loading of gas system during the day.
Applied Sciences
The growing popularity of data outsourcing to third-party cloud servers has a downside, related t... more The growing popularity of data outsourcing to third-party cloud servers has a downside, related to the serious concerns of data owners about their security due to possible leakage. The desire to reduce the risk of loss of data confidentiality has become a motivating start to developing mechanisms that provide the ability to effectively use encryption to protect data. However, the use of traditional encryption methods faces a problem. Namely, traditional encryption, by making it impossible for insiders and outsiders to access data without knowing the keys, excludes the possibility of searching. This paper presents a solution that provides a strong level of confidentiality when searching, inserting, modifying, and deleting the required sensitive data in a remote database whose data are encrypted. The proposed SQL query processing technique allows the DBMS server to perform search functions over encrypted data in the same way as in an unencrypted database. This is achieved through the ...
Information
The problem of nonlinear substitution generation (S-boxes) is investigated in many related works ... more The problem of nonlinear substitution generation (S-boxes) is investigated in many related works in symmetric key cryptography. In particular, the strength of symmetric ciphers to linear cryptanalysis is directly related to the nonlinearity of substitution. In addition to being highly nonlinear, S-boxes must be random, i.e., must not contain hidden mathematical constructs that facilitate algebraic cryptanalysis. The generation of such substitutions is a complex combinatorial optimization problem. Probabilistic algorithms are used to solve it, for instance the simulated annealing algorithm, which is well-fitted to a discrete search space. We propose a new cost function based on Walsh–Hadamard spectrum computation, and investigate the search efficiency of S-boxes using a simulated annealing algorithm. For this purpose, we conduct numerous experiments with different input parameters: initial temperature, cooling coefficient, number of internal and external loops. As the results of the ...
Challenges to national defence in contemporary geopolitical situation, Nov 3, 2022
This paper presents the result of the study of network intrusion detection using machine learning... more This paper presents the result of the study of network intrusion detection using machine learning algorithms. The creation and training of such algorithms is seriously limited by the small number of actual datasets available for public access. The CSE-CIC-IDS2018 data set, used in research, includes 7 subsets of different attack scenarios. Each subset is labeled using a few subtypes of a given attack or normal behavior. That is why the problem of network attack detection has been considered a multiclassification problem. Some of the most popular classifiers will be tested on the chosen data set. Classification algorithms are developed using a standard Python programming environment and the specialized machine learning library Scikit-learn. In the paper, a comparative analysis of the results was performed based on the the application of Random Forest, XGBoost, LR, and MLP classifiers.
2017 9th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS), 2017
Intensive development of information systems has led to an increase in malicious software, which ... more Intensive development of information systems has led to an increase in malicious software, which is associated with the emergence of new types of cyber attacks. Expanding impact of cyber attacks aimed at a variety of resources information system initiates creation of special countermeasures that can be effective in the emergence of new types of threats from unknown or ill-defined properties. There are enough effective developments, are used to solve problems of cyber attacks identification, for example, the method of linguistic etalons formation for the detection of intrusion systems, which does not disclose the mechanism of the formation of etalons settings for sniffing attacks. In this work, was developed etalons model of linguistic variables to detect sniffing attacks, which is due to assess the state of the information system and the process of forming the parameters of etalons will allow to formalize the process of obtaining the parameters of etalons for a given linguistic variables in specific environment in solving attacks detection tasks on computer systems.
Information & Security: An International Journal, 2016
Leading companies in the field of ICT often provide training courses. Such courses are found attr... more Leading companies in the field of ICT often provide training courses. Such courses are found attractive by students, especially students specializing in technical disciplines. In this article, we review courses provided by Cisco Systems, describe their organization, nomenclature and structure, and provide recommendations on their use in the academic curricula in the field of information and communications security. The inclusion of such courses in the academic curricula is considered beneficial in terms of competitiveness of graduates on current and foreseen labour markets.
Review of main approaches of gas consumption prognosis and analysis models is given here. Most of... more Review of main approaches of gas consumption prognosis and analysis models is given here. Most of them are long-term prognosis methods, which take into account some weather conditions (mostly temperature as most significant one), few short-term methods works only for non-heating period. Unlike the existing methods, new approach gives a possibility to analyze and calculate prognosis values of gas consumption in heating season taking into consideration its cyclic nature and temperature of environment at the same time. It helps to monitor, analyze, plan and manage loading of gas system during the day.