Oleksandr Korystin

Work place: State Scientifically Research Institute of the MIA of Ukraine, Kyiv, Ukraine

E-mail: alex@korystin.pro

Website: https://orcid.org/0000-0001-9056-5475

Research Interests: Models of Computation, Information-Theoretic Security, Information Security, Application Security, Artificial Intelligence


Oleksandr Korystin

DSc, PhD, Professor. In 2009 he received DSc degree in information law from NAIA. In 2014 he received Professor degree. Honored Academic of Science and Technology of Ukraine.

Chief Research Scientist of the Criminological Research Laboratory of the State Scientific Research Institute of the Ministry of Internal Affairs of Ukraine. In 2014–2016 – Rector of the Odesa State University of Internal Affairs. Member of the Expert Council of the Ministry of Education and Science of Ukraine on legal sciences. Research interests: criminology; economic security; cybersecurity; intelligence; methodology of strategical (SWOT-analysis; risks assessment); counteraction to the hybrid threat.

Author Articles
The Method of Semantic Image Segmentation Using Neural Networks

By Ihor Tereikovskyi Denys Chernyshev Liudmyla Tereikovska Oleksandr Korystin Oleh Tereikovskyi Zhengbing Hu

DOI: https://doi.org/10.5815/ijigsp.2022.06.01, Pub. Date: 8 Dec. 2022

Currently, the means of semantic segmentation of images, which are based on the use of neural networks, are increasingly being used in computer systems for various purposes. Despite significant progress in this industry, one of the most important unsolved problems is the task of adapting a neural network model to the conditions for selecting an object mask in an image. The features of such a task necessitate determining the type and parameters of convolutional neural networks underlying the encoder and decoder. As a result of the research, an appropriate method has been developed that allows adapting the neural network encoder and decoder to the following conditions of the segmentation problem: image size, number of color channels, acceptable minimum segmentation accuracy, acceptable maximum computational complexity of segmentation, the need to label segments, the need to select several segments, the need to select deformed , displaced and rotated objects, allowable maximum computational complexity of training a neural network model, allowable training time for a neural network model. The main stages of the method are related to the following procedures: determination of the list of image parameters to be registered; formation of training example parameters for the neural network model used for object selection; determination of the type of CNN encoder and decoder that are most effective under the conditions of the given task; formation of a representative educational sample; substantiation of the parameters that should be used to assess the accuracy of selection; calculation of the values of the design parameters of the CNN of the specified type for the encoder and decoder; assessment of the accuracy of selection and, if necessary, refinement of the architecture of the neural network model. The developed method was verified experimentally on examples of semantic segmentation of images containing objects such as a car. The obtained experimental results show that the application of the proposed method allows, avoiding complex long-term experiments, to build a NN that, with a sufficiently short training period, ensures the achievement of image segmentation accuracy of about 0.8, which corresponds to the best systems of similar purpose. It is shown that it is advisable to correlate the ways of further research with the development of approaches to the use of special modules such as ResNet, Inception and mechanisms of the Partial convolution type used in modern types of deep neural networks to increase their computational efficiency in the encoder and decoder.

[...] Read more.
Risk Forecasting of Data Confidentiality Breach Using Linear Regression Algorithm

By Oleksandr Korystin Svyrydiuk Nataliia Olena Mitina

DOI: https://doi.org/10.5815/ijcnis.2022.04.01, Pub. Date: 8 Aug. 2022

The paper focuses on the study of cyber security in Ukraine and creation of a predictive model for reducing the risk of identified cyber threats. Forecasting is performed using a linear regression model, taking into account the optimal dependence of specific threats in the field of cyber security of Ukraine on variables characterizing capabilities / vulnerabilities of cyber security. An unique empirical base was used for the analysis, which was formed on the basis of an expert survey of the cyber security system’s subjects in Ukraine. In order to increase the representativeness of the research, based on the selection of reliable expert population, data cleaning is provided. Methodological research is based on a risk-oriented approach, which provided a risk assessment of the spread of cyber threats and, on this basis, the determination of capabilities / vulnerabilities of the cyber security system in Ukraine. The value of the research is formed not only by assessing the risks of the spread of cyber threats, but by a more in-depth analysis of the dependence of the cyber threats’ level on the vulnerability of the cyber security system based on the search for optimal and statistically significant relationships. The experiment was conducted on the basis of determining the optimal model for forecasting the risk of the spread of one of the most significant threats in Ukraine – data confidentiality breach (54.67%), depending on the variables that characterize the capabilities / vulnerabilities of the cyber security system in Ukraine. The experiment showed that the optimal model emphasizes the predictors characterizing the vulnerability of the organizational cyber security system – "Departmental level of cybersecurity monitoring" and capabilities: "The level of use of risk management approaches at the operational level" and "The level of methodological support for cybersecurity of the critical infrastructure system".

[...] Read more.
Other Articles