№ 3 (61)

The goal of the investigation: finding ways to improve the effectiveness of countering insiders in large information systems by combining methods of their detection. Research methods: analytical review of relevant scientific publications, conceptual modeling, formalization, categorical approach, expert and theoretical combination, synthesis, algorithmization.
Results: a generalized list is obtained and a partially formalized model of combining qualitatively different methods of detecting insiders in large information systems is developed; an expert forecast of 21 combinations from 7 of these methods is proposed, a theoretical evaluation of the success of their combination is given; a combined method of detecting insiders is synthesized, the algorithm of which is given in the form of pseudo code. The scientific novelty is determined by the author's approach to combining methods on the basis of a categorical space with axes along the following pairs of antagonistic elements: normal vs. abnormal, static vs. dynamic, subject vs. object. Most of the combinations of methods are proposed for the first time.
Keywords:  large information system, information security, insider, detection method, combination of methods.

1. Минаков С. С. Основные криптографические механизмы защиты данных, передаваемых в облачные сервисы и сети хранения 1. Ponemon Cost of Insider Threats: Global Report, 2023. URL: https://www.dtexsystems.com/resource-ponemon-insider-risks-global-report/ (дата доступа: 02.05.2024)
2. Verizon 2023 Data Breach Report: A Bulleted Summary. URL: https://rublon.com/blog/verizon-2023-data-breach-report-summary/ (дата доступа: 02.05.2024)
3. Власов Д. С. К вопросу о мотивации инсайдера организации и способах его классификации // Электронный сетевой политематический журнал «Научные труды КубГТУ». 2022. № 1. С. 128–147.
4. Buinevich M., Izrailov K., Kotenko I., Ushakov I., Vlasov D. Approach to combining different methods for detecting insiders // The proceedings of 4th International Conference on Future Networks and Distributed Systems (New York, USA, 2020). Iss. 26. PP. 1–6. DOI: 10.1145/3440749.3442619
5. Duncan A., Creese S., Goldsmith M. A Combined Attack-Tree and Kill-Chain Approach to Designing Attack-Detection Strategies for Malicious Insiders in Cloud Computing // The proceedings of International Conference on Cyber Security and Protection of Digital Services (Oxford, UK, 2019). IEEE, 2019, PP. 1–9. DOI: 10.1109/CyberSecPODS.2019.8885401
6. Kammüller F., Probst C. W. Combining Generated Data Models with Formal Invalidation for Insider Threat Analysis // The proceedings of Security and Privacy Workshops (San Jose, CA, USA, 2014). 2014. PP. 229–235. DOI: 10.1109/SPW.2014.45
7. Garfinkel S. L. Beebe N. Liu L. Maasberg M. Detecting threatening insiders with lightweight media forensics // The proceedings of International Conference on Technologies for Homeland Security (Waltham, MA, USA, 2013). IEEE, 2013. PP. 86-92. DOI: 10.1109/THS.2013.6698981 8. Liu A. Y., Lam D. N. Using Consensus Clustering for Multi-view Anomaly Detection // The proceedings of Symposium on Security and Privacy Workshops (San Francisco, CA,  USA, 2021). IEEE, 2012. PP. 117–124. DOI: 10.1109/SPW.2012.18
9. Ackerman D., Mehrpouyan H. Modeling human behavior to anticipate insider attacks via System Dynamics // The proceedings of Symposium on Theory of Modeling and Simulation (Pasadena, CA, USA, 2016). 2016. PP. 1–6. DOI: 10.23919/TMS.2016.7918809
10. Sarma M. S., Srinivas Y., Abhiram M., Ullala L., Prasanthi M. S., Rao J. R. Insider Threat Detection with Face Recognition and KNN User
Classification // The proceedings of International Conference on Cloud Computing in Emerging Markets (Bangalore, India, 2017), IEEE, 2017. PP. 39–44, DOI: 10.1109/CCEM.2017.16.
11. Буйневич М. В., Власов Д. С. Сравнительный обзор способов выявления инсайдеров в информационных системах // Информатизация и связь. 2019. № 2. С. 83–91. DOI: 10.34219/2078-8320-2019-10-2-83-91
12. Власов Д. С. Мультикритериальная модель систематизации способов обнаружения инсайдера // Вопросы кибербезопасности. 2024. № 2 (60). С. 66–73. DOI: 10.21681/2311-3456-2024-2-66-73
13. Буйневич М. В., Израилов К. Е., Матвеев В. В., Покусов В. В. Способ вариативной классификации уязвимостей в программном коде. Часть 1. Стратификация и категориальное деление // Автоматизация в промышленности. 2021. № 11. С. 42–49. DOI: 10.25728/avtprom.2021.11.09
14. Нашивочников Н. В. Выявление отклонений в поведенческих паттернах пользователей корпоративных информационных ресурсов с использованием топологических признаков // Вопросы кибербезопасности. 2023. № 4 (56). С. 12–22. DOI: 10.21681/2311-3456-2023-4-12-22.
15. Лебедев Д. В., Васильев Н. В. Метод выделения семантически согласованных групп пользователей социальных медиа-платформ // Техника средств связи. 2021. № 4 (156). С. 20–33.
16. Buinevich M., Izrailov K., Vladyko A. Metric of vulnerability at the base of the life cycle of software representations // The proceedings of 20th International Conference on Advanced Communication Technology (Chuncheon, South Korea, 2018). IEEE, 2018. PP. 1–8. URL: https://ieeexplore.ieee.org/document/8323940.
17. Buinevich M., Izrailov K., Vladyko A. Testing of Utilities for Finding Vulnerabilities in the Machine Code of Telecommunication Devices // The proceedings of 19th International Conference on Advanced Communication Technology (Pyeongchang, South Korea, 2017). IEEE, 2017. PP. 408–414. URL: https://ieeexplore.ieee.org/document/7890122
18. Поляничко М. А. Методика обнаружения аномального взаимодействия пользователей с информационными активами для выявления инсайдерской деятельности // Труды учебных заведений связи. 2020. Т. 6. № 1. С. 94–98. DOI: 10.31854/1813-324X-2020-6-1-94-98 
19. Man D., Wang Y., Yang W., Wang W. A Combined Prediction Method for Network Security Situation // The proceedings of International Conference on Computational Intelligence and Software Engineering (Wuhan, China, 10-12 December 2010). 2010. PP. 1–4. DOI: 10.1109/CISE.2010.5676911
20. Lim S.-H., Yun S., Lim J., Yi O. Formalizing the design, evaluation, and analysis of quality of protection in wireless networks // Journal of Communications and Networks(). 2009. Vol. 11. No. 6. PP. 634-644. DOI: 10.1109/JCN.2009.6388417
21. Yu J., Oh H., Kim M., Jung S. Unusual Insider Behavior Detection Framework on Enterprise Resource Planning Systems Using Adversarial Recurrent Autoencoder // IEEE Transactions on Industrial Informatics. Vol. 18. No. 3. PP. 1541–1551. DOI: 10.1109/TII.2021.3090362
22. Jeridi W., Benabdallah S., Hamdi M., Boudriga N. Dynamic expert weighing for Security Risk Analysis team synergy // The proceedings of Second International Conference on Engineering System Management and Applications (Arab Emirates, 30 March 2010 - 01 April 2010). 2010. PP. 1–8.
23. Уткин О. В., Власов Д. С., Ильин А. В., Ефременков Е. Ю. Методика оценки деятельности должностного лица ЦУКС МЧС России // Подготовка кадров в системе предупреждения и ликвидации последствий чрезвычайных ситуаций: материалы международной научно-практической конференции. 2017. С. 227–228.
24. Mescheryakov S., Shchemelinin D., Izrailov K., Pokussov V. Digital cloud environment: present challenges and future forecast // Future Internet. 2020. Vol. 12. Iss. 5. PP. 82. DOI: 10.3390/fi12050082
25. Мадиева К. З. Искусственный интеллект и социотехнические угрозы безопасности информации // Журнал высоких гуманитарных технологий. 2024. № 1 (4). С. 38–45.

The purpose of research: to present a framework within which metrics of attack trees containing conjunction, disjunction and sequential conjunction gates can be developed and calculated.
Methods: mathematical logic, linear logic, machinery of the category theory Results: An approach to the construction of metrics on dynamic attack trees is proposed. A metric is considered as an algebra over the operad of attack trees with modular composition. Such metrics are called consistent with the modular composition. It is shown that the bottom-up calculated metrics are consistent with the modular composition. The presence of sequential conjunction nodes in the attack tree generates a directed graph on the set of the terminal vertices. If this graph is acyclic, a metric consistent with the modular composition have an unambiguous interpretation. If there are cycles on the graph, the unambiguity of interpretation is due to the substantial properties of the basic attack steps. The paper shows that the meaningful properties of atomic elements can be represented by equations in the algebra of terms. For this purpose, the concept of a disjunctive normal form of a dynamic attack tree is introduced and it is shown that any tree can be represented in this form by transformations using only basic identities. The scientific novelty of the results obtained consists in the application of operads to determine metrics on dynamic attack trees.
Keywords: attack tree, sequential conjunction, disjunctive normal form, linear logic, modular category,
operad, functor. 

1. Agyepong E. Cherdantseva Y., Reinecke P., Burnap P. Challenges and performance metrics for security operations center analysts: a systematic review //Journal of Cyber Security Technology. – 2020. – Т. 4. – №. 3. – С. 125–152.
2. Ali A. T., Gruska D. Dynamic attack trees methodology // 2022 Interdisciplinary Research in Technology and Management (IRTM). – IEEE, 2022. – С. 1–9.
3. Bossuat A., Kordy B. Evil Twins: Handling Repetitions in Attack–Defense Trees: A Survival Guide //Graphical Models for Security: 4th International Workshop, GraMSec 2017, Santa Barbara, CA, USA, August 21, 2017, Revised Selected Papers 4. – Springer International Publishing, 2018. – С. 17–37.
4. Budde C. E., Stoelinga M. Efficient algorithms for quantitative attack tree analysis //2021 IEEE 34th Computer Security Foundations Symposium (CSF). – IEEE, 2021. – С. 1-15.
5. Buldas, A., Gadyatskaya, O., Lenin, A., Mauw, S., & Trujillo-Rasua, R. Attribute evaluation on attack trees with incomplete information // Computers & Security. – 2020. – Т. 88. – С. 101630.
6. Eades III H., Jiang J., Bryant A. On linear logic, functional programming, and attack trees //Graphical Models for Security: 5th International Workshop, GraMSec 2018, Oxford, UK, July 8, 2018, Revised Selected Papers 5. – Springer International Publishing, 2019. – С. 71–89.
7. Федорченко Е. В., Котенко И. В., Федорченко А. В., Новикова Е. С., Саенко И. Б. Оценивание защищенности информационных систем на основе графовой модели эксплойтов //Вопросы кибербезопасности. – 2023. – №. 3. – С. 23–36.
8. Konsta, A. M., Lafuente, A. L., Spiga, B., & Dragoni, N. Survey: Automatic generation of attack trees and attack graphs //Computers & Security. – 2024. – Т. 137. – С. 103602.
9. Lallie H. S., Debattista K., Bal J. A review of attack graph and attack tree visual syntax in cyber security //Computer Science Review. 2020. Т. 35. С. 100219. https://doi.org/10.1016/j.cosrev.2019.100219
10. Lopuhaä-Zwakenberg M., Budde C. E., Stoelinga M. Efficient and Generic Algorithms for Quantitative Attack Tree Analysis // IEEE Transactions on Dependable and Secure Computing. 20(5). 2022. – 4169–4187. DOI: 10.1109/TDSC.2022.3215752
11. Lopuhaä-Zwakenberg M., Stoelinga M. Attack time analysis in dynamic attack trees via integer linear programming //International Conference on Software Engineering and Formal Methods. – Cham : Springer Nature Switzerland, 2023. – С. 165–183.
12. Lopuhaä-Zwakenberg M. Attack tree metrics are operad algebras //arXiv preprint arXiv:2401.10008. – 2024.
13. Wu, Z., Hu, J., Zhang, X., & Ren, W. timeTree: How to Represent Time Sequence in a Threat Tree //2022 IEEE 24th Int Conf on High Performance Computing & Communications; 8th Int Conf on Data Science & Systems; 20th Int Conf on Smart City; 8th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys). – IEEE, 2022. – С. 2373–2378.
14. Zeng J., Wu, S., Chen, Y., Zeng, R., & Wu, C.Survey of attack graph analysis methods from the perspective of data and knowledge processing // Security and Communication Networks. 2019. Т. 2019. Article ID 2031063, 16 С., 2019. https://doi.org/10.1155/2019/2031063

The purpose of the article: adaptation of the logical-probabilistic method of evaluating complex systems to the tasks of building information security systems in a multi-agent system. Research method: during the research, the main provisions of the methodology of structural analysis, system analysis, decision theory, methods of evaluating events under the condition of incomplete information were used. The result: this article continues the consideration of information security issues based on the analysis of the relationship between the subjects and the object of protection. It is shown that the state of the agent's relations can be obtained on the basis of appropriate assessments of states at the level of information resources and information flows. It is shown that the assessment of states can be carried out at both qualitative and quantitative levels, based on sets of events and messages formed in the agent as a result of external influences. The obtained results provide a reasonable calculation and application of probabilistic characteristics for the subsequent application of the logical-probabilistic method in the analysis of these relations. Scientific novelty: consideration of information security issues using the apparatus of mathematical and logical relations. The possibility of determining quantitative and qualitative assessments of the agent's condition based on events and messages generated in the process of functioning is shown. Methods for assessing the state of relations at the level of information resources and information flows through the level of trust have been developed. A lower estimate of the level of confidence in finding an object in a certain state has been determined. The relationships between events and messages from the state templates and the current set are investigated, which can be used as criteria in the design of the corresponding IS subsystems and their components from the point of view of information security.
Keywords:  information security model, assessment of complex systems, logical-probabilistic method, theory
of relations, system analysis.

1. Рябинин И. А. Решение одной задачи оценки надежности структурно-сложной системы разными логико-вероятностными методами / И. А. Рябинин, А. В. Струков // Моделирование и анализ безопасности и риска в сложных системах, Санкт-Петербург, 19–21 июня 2019 года. – Санкт-Петербург: Санкт-Петербургский государственный университет аэрокосмического
приборостроения, 2019. – С. 159–172.
2. Демин А. В. Глубокое обучение адаптивных систем управления на основе логико-вероятностного подхода / А. В. Демин // Известия Иркутского государственного университета. Серия: Математика. – 2021. – Т. 38. – С. 65–83.
3. Викторова В. С. Вычисление показателей надежности в немонотонных логико-вероятностных моделях многоуровневых систем / В. С. Викторова, А. С. Степанянц // Автоматика и телемеханика. – 2021. – № 5. – С. 106–123.
4. Леонтьев А. С. Математические модели оценки показателей надежности для исследования вероятностно-временных характеристик многомашинных комплексов с учетом отказов / А. С. Леонтьев, М. С. Тимошкин // Международный научно-исследовательский журнал. – 2023. – № 1(127). С. 1–13.
5. Пучкова Ф. Ю. Логико-вероятностный метод и его практическое использование / Ф. Ю. Пучкова // Информационные технологии в процессе подготовки современного специалиста: Межвузовский сборник научных трудов / Министерство просвещения Российской Федерации; Федеральное государственное бюджетное образовательное учреждение высшего образования «Липецкий государственный педагогический университет имени П. П. Семенова-Тян-Шанского». Том Выпуск 25. – Липецк: Липецкий государственный педагогический университет имени П. П. Семенова-Тян-Шанского, 2021. – С. 187–193.
6. Россихина Л. В. О применении логико-вероятностного метода И. А. Рябинина для анализа рисков информационной безопасности / Л. В. Россихина, О. О. Губенко, М. А. Черноситова // Актуальные проблемы деятельности подразделений УИС: Сборник материалов Всероссийской научно-практической конференции, Воронеж, 20 октября 2022 года. – Воронеж: Издательско-полиграфический центр «Научная книга», 2022. – С. 108-109.
7. Карпов А. В. Модель канала утечки информации на объекте информатизации / А. В. Карпов // Актуальные проблемы инфотелекоммуникаций в науке и образовании (АПИНО 2018): VII Международная научно-техническая и научно-методическая конференция. Сборник научных статей. В 4-х томах, Санкт-Петербург, 28 февраля – 01 марта 2018 года / Под редакцией С. В. Бачевского. Том 2. – Санкт-Петербург: Санкт-Петербургский государственный университет телекоммуникаций им. проф. М. А. Бонч-Бруевича, 2018. – С. 378–382.
8. Методика кибернетической устойчивости в условиях воздействия таргетированных кибернетических атак / Д. А. Иванов,
М. А. Коцыняк, О. С. Лаута, И. Р. Муртазин // Актуальные проблемы инфотелекоммуникаций в науке и образовании (АПИНО
2018): VII Международная научно-техническая и научно-методическая конференция. Сборник научных статей. В 4-х томах,
Санкт-Петербург, 28 февраля – 01 марта 2018 года / Под редакцией С.В. Бачевского. Том 2. – Санкт-Петербург: Санкт-Петербургский государственный университет телекоммуникаций им. проф. М.А. Бонч-Бруевича, 2018. – С. 343–346.
9. Елисеев Н. И. Оценка уровня защищенности автоматизированных информационных систем юридически значимого электронного
документооборота на основе логико-вероятностного метода / Н. И. Елисеев, Д. И. Тали, А. А. Обланенко // Вопросы кибербезопасности. – 2019. – № 6(34). – С. 7–16.
10. Коцыняк М. А. Математическая модель таргетированной компьютерной атаки / М. А. Коцыняк, О. С. Лаута, Д. А. Иванов // Наукоемкие технологии в космических исследованиях Земли. – 2019. – Т. 11, № 2. – С. 73–81.
11. Белякова, Т. В. Функциональная модель процесса воздействия целевой компьютерной атаки / Т. В. Белякова, Н. В. Сидоров, М. А. Гудков // Радиолокация, навигация, связь: Сборник трудов XXV Международной научно-технической конференции, посвященной 160-летию со дня рождения А. С. Попова. В 6 томах, Воронеж, 16–18 апреля 2019 года. Том 2. – Воронеж: Воронежский государственный университет, 2019. – С. 108–111.
12. Калашников А. О. Применение логико-вероятностного метода в информационной безопасности (Часть 1) / А. О. Калашников, К. А. Бугайский, Д. С. Бирин, Б. О. Дерябин, С. О. Цепенда, К. В. Табаков // Вопросы кибербезопасности. – 2023. – № 4 (56). – С. 23–32. DOI: 10.21681/2311-3456-2023-4-23-32
13. Калашников А. О. Применение логико-вероятностного метода в информационной безопасности (Часть 2) / А. О. Калашников, К. А. Бугайский, Е. И. Аникина, И. С. Перескоков, Ан. О. Петров, Ал. О. Петров, Е. С. Храмченкова, А. А. Молотов // Вопросы кибербезопасности. – 2023. – № 5 (57). – С. 113–127. С. 23–32. DOI: 10.21681/2311-3456-2023-5-113-127
14. Калашников А. О. Применение логико-вероятностного метода в информационной безопасности (Часть 3) / А. О. Калашников, К. А. Бугайский, Е. И. Аникина, И. С. Перескоков, Ан. О. Петров, Ал. О. Петров, Е. С. Храмченкова, А. А. Молотов // Вопросы кибербезопасности. – 2023. – № 6 (58). – С. 20–34. С. 23–32. DOI: 10.21681/2311-3456-2023-6-20-34
15. Калашников А. О. Инфраструктура как код: формируется новая реальность информационной безопасности / А. О. Калашников, К. А. Бугайский // Информация и безопасность. – 2019. – Т. 22, № 4. – С. 495–506.
16. Бугайский К. А. Расширенная модель открытых систем (Часть 1) / К. А. Бугайский, Д. С. Бирин, Б. О. Дерябин, С. О. Цепенда // Информация и безопасность. – 2022. – Т. 25, № 2. – С. 169–178.
17. Котенко И. В. Технологии больших данных для корреляции событий безопасности на основе учета типов связей / И. В. Котенко, А. В. Федорченко, И. Б. Саенко, А. Г. Кушнеревич // Вопросы кибербезопасности. – 2017. – № 5 (24). – С. 2–16. С. 23–32. DOI: 10.21681/2311-3456-2017-5-2-16
18. Дойникова Е. В. Совершенствование графов атак для мониторинга кибербезопасности: оперирование неточностями, обработка циклов, отображение инцидентов и автоматический выбор защитных мер / Е. В. Дойникова, И. В. Котенко // Труды СПИИРАН. – 2018. – № 2 (57). – С. 211–240.
19.	 Калашников, А. О. Модель оценки безопасности сложной сети. (часть 1) / А. О. Калашников, К. А. Бугайский // Вопросы кибербезопасности. – 2022. – № 4 (50). – С. 26–38. DOI:10.21681/2311-3456-2022-4-26-38

The purpose of the study: investigation of the effectiveness of BERT modifications in solving the problem of predicting categories of vulnerabilities (CVE) for information system devices based on their configurations (CPE URIs). Research methods: natural language processing methods, cross-validation of artificial intelligence models, optimization of hyperparameters of artificial intelligence models. Results obtained: based on the content of open vulnerability databases, we collected a data set that establishes relationships between preprocessed CPE URIs and the identified 24 CVE categories; we investigated the effectiveness of BERT, RoBERTa, XLM-RoBERTa and DeBERTaV3 in solving the problem of predicting CVE categories based on CPE URIs; we trained optimized BERT model to solve the problem of vulnerabilities prediction; we compared the resulting solution with available state-of-the-art. Scientific novelty: this work is one of the first in predicting device vulnerabilities based on their configuration, which emphasizes its scientific significance and novelty. Moreover, it is also one of the first works to explore BERT for the task of vulnerability prediction. Contribution: Levshun D. S., Kotenko I. V. - selection and formulation of the research problem; Levshun D. S., Vesnin D. V. - selection of solutions, software implementation and experiments; Levshun D. S., Kotenko I. V. - discussion of the experimental results, analysis of the results obtained.
Keywords:  information security, vulnerability analysis, BERT, CVE, CPE, CVSS, NVD. 

1. Li Y., Huang G., Wang C., Li Y. Analysis framework of network security situational awareness and comparison of implementation methods // EURASIP Journal on Wireless Communications and Networking. 2019. Vol. 2019. P. 1–32. DOI: 10.1186/s13638-019-1506-1.
2. Израилов К. Е., Левшун Д. С., Чечулин А. А. Модель классификации уязвимостей интерфейсов транспортной инфраструктуры «умного города» // Системы управления, связи и безопасности. 2021. №. 5. С. 199–223. DOI: 10.24412/2410-9916-2021-5-199-223. 
3. Lallie H. S., Debattista K., Bal J. A review of attack graph and attack tree visual syntax in cyber security // Computer Science Review. 2020. Vol. 35. P: 100219. DOI: 10.1016/j.cosrev.2019.100219.
4. Федорченко Е. В., Котенко И. В., Федорченко А. В., Новикова Е. С., Саенко И. Б. Оценивание защищенности информационных систем на основе графовой модели эксплойтов // Вопросы кибербезопасности. 2023. № 3 (55). С.23-36. DOI:10.21681/2311-3456-2023-3-23-36.
5. Kotenko I., Izrailov K., Buinevich M., Saenko I., Shorey R. Modeling the Development of Energy Network Software, Taking into Account the Detection and Elimination of Vulnerabilities // Energies. 2023. Volume 16, Issue 13, 5111. P.1-40. https://doi.org/10.3390/en16135111.
6. Levshun D., Chechulin A. Vulnerability Categorization for Fast Multistep Attack Modelling // Proceedings of the 33rd Conference of the Open Innovations Association FRUCT. May 24-26, Zilina, Slovakia. 2023. P. 169-175. DOI: 10.23919/FRUCT58615.2023.10143048.
7. Devlin J., Chang M.-W., Lee K., Toutanova K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding // Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol.1. 2019. P.4171–4186. DOI:10.18653/v1/N19-1423.
8. Katsadouros E., Patrikakis C. A Survey on Vulnerability Prediction using GNNs // Proceedings of the 26th Pan-Hellenic Conference on Informatics. 2022. P. 38-43. DOI: 10.1145/3575879.3575964.
9. Eberendu A. C., Udegbe V. I., Ezennorom E. O., Ibegbulam A. C., Chinebu T. I. A systematic literature review of software vulnerability detection // European Journal of Computer Science and Information Technology. 2022. Vol. 10. No. 1. P. 23–37. DOI: 10.37745/ejcsit.2013.
10. Huang G., Li Y., Wang Q., Ren J., Cheng Y., Zhao, X. Automatic classification method for software vulnerability based on deep neural network // IEEE Access. 2019. Vol. 7. P. 28291-28298. DOI: 10.1109/ACCESS.2019.2900462.
11. Shen Z., Chen S. A survey of automatic software vulnerability detection, program repair, and defect prediction techniques // Security and Communication Networks. 2020. Vol. 2020. P. 1–16. DOI: 10.1155/2020/8858010.
12. Kalouptsoglou I., Kalouptsoglou I., Siavvas M., Ampatzoglou A., Kehagias D., Chatzigeorgiou A. Software vulnerability prediction: A systematic mapping study // Information and Software Technology. 2023. P. 107303. DOI: 10.1016/j.infsof.2023.107303.
13. Croft R., Xie Y., Babar M. A. Data preparation for software vulnerability prediction: A systematic literature review // IEEE Transactions on Software Engineering. 2022. Vol. 49. No. 3. P. 1044-1063. DOI: 10.1109/TSE.2022.3171202.
14. Akiba T., Sano S., Toshihiko Y., Ohta T., Koyama M. Optuna: A next generation hyperparameter optimization framework // Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining. 2019. P. 2623–2631. DOI: 10.1145/3292500.3330701.
15. Liu Z., Ott M., Goyal N., Du J., Joshi M., Chen D., Levy O., Lewis M., Zettlemoyer L., Stoyanov V. A robustly optimized BERT pre-training approach with post-training // Proceedings of the China National Conference on Chinese Computational Linguistics. Cham: Springer International Publishing, 2021. P. 471–484. DOI: 10.48550/arXiv.1907.11692.
16. Conneau A., Chaudhary V., Wenzek G., Guzman F., Grave E., Ott M., Zettlemoyer L., Stoyanov V. Unsupervised Cross-lingual Representation Learning at Scale // Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics. 2020. DOI: 10.48550/arXiv.1911.02116.
17. He P., Gao J., Chen W. DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing // Proceedings of the Eleventh International Conference on Learning Representations. 2022. DOI: 10.48550/arXiv.2111.09543.
18. Levshun D. Comparative analysis of machine learning methods in vulnerability categories prediction based on configuration similarity // Proceedings of the 16th International Symposium on Intelligent Distributed Computing (IDC-2023). September 13–15, Hamburg, Germany. 2023. P. 231–242.
19. Levshun D., Vesnin D. Exploring BERT for Predicting Vulnerability Categories in Device Configurations // Proceedings of the 10th International Conference on Information Systems Security and Privacy (ICISSP 2024). February 26–28, Rome, Italy. 2024. P. 452–461. DOI: 10.5220/0012471800003648.

The purpose of the study: the formation of an algorithm for assessing trust in the information security audit process, consisting of a sequential multi-stage analysis of evidence of trust according to the hierarchical model «object-criteria-metrics». The research methods are based on the analysis of the domestic and foreign regulatory framework, scientific publications, as well as on the application of Harrington's desirability function.
Result: an algorithm for assessing trust was formed, consisting of a sequential multi-stage analysis of evidence of trust according to the hierarchical model «object-criteria-metrics». In accordance with this hierarchical model, metrics are calculated based on the analysis of evidence of trust, criteria are calculated based on the values of the metrics, and the level of trust is calculated based on the values of the criteria. Metrics and criteria for assessing trust were defined. The calculation of trust in the information security audit process is based on the Harrington desirability function and GOST R 57580.2-2018. In this case, metrics, as a numerical result of assessing evidence of trust, act as partial signs of desirability, criteria - as partial functions of desirability, and the level of confidence in the information security audit process - as a generalized function of desirability. The resulting algorithm for assessing trust in information security audit processes will be integrated into the general algorithm for assessing trust in subjects of information exchange, which includes an analysis of a number of information security processes, one of which is audit. The scientific novelty lies in the proposal of a dynamic method for monitoring the information security audit process, based on the analysis of objective evidence and subject to automation. Trust assessment, as a dynamic measure of control of information security processes, is designed to minimize labor and time costs when monitoring information security processes.
Keywords: trust, methodology, conformity assessment, audit trust, process assessment, trusted interaction,
information security, cybersecurity. 

1. Кузнецова Н. М. Решение задачи автоматизации процессов защиты стратегически важных ресурсов предприятия от комплексных кибератак на основе анализа тактик злоумышленников / Н. М. Кузнецова, Т. В. Карлова, А. В. Бекмешов // Вестник
Брянского государственного технического университета. 2020. №7 (92). URL: https://cyberleninka.ru/article/n/reshenie-zadachiavtomatizatsii-protsessov-zaschity-strategicheski-vazhnyh-resursov-predpriyatiya-ot-kompleksnyh-kiber-atak-na-osnove (дата обращения: 12.02.2023).
2. Макаренко С. И. Тестирование на проникновение на основе стандарта NIST SP 800–115 // Вопросы кибербезопасности. –
2022. – №3 (49). – С. 44–57. DOI:10.21681/2311-3456-2022-3-44-49
3. К вопросу анализа нормативно-правовых документов по информационной безопасности автоматизированных систем органов
внутренних дел Российской Федерации для оценки уровня их защищенности / Е. А. Рогозин, И. Г. Дровникова, А. О. Ефимов,
В. Р. Романова // Вестник Дагестанского государственного технического университета. Технические науки. – 2022. – № 4 (49). – С. 97–103.
4. Селифанов В. В. Вопросы оценки доверия к системе управления рисками / В. В. Селифанов, В. В. Аникеева, И. А. Огнев // Безопасность цифровых технологий. – 2023. – № 1 (108). – С. 69–82. – DOI: 10.17212/2782–2230–2023–1–69–82.
5. Построение адаптивной трехуровневой модели процессов управления системой защиты информации объектов критической
информационной инфраструктуры / А. С. Голдобина, Ю. А. Исаева, В. В. Селифанов, А. М. Климова, П. С. Зенкин // Доклады
Томского государственного университета систем управления и радиоэлектроники. – 2018. – №21. – С. 51–58.
6. Roy S. S. Enhanced trust management for building trustworthy social internet of things network / S.S. Roy, B.J.R. Sahu, S. Dash // IET Networks. – 2024. – № . – С. 1–11.
7. Access Control, Key Management, and Trust for Emerging Wireless Body Area Networks / A. S. Shahraki, H. Lauer, M. Grobler, A. Sakzad, C. Rudolph // Sensors. – 2023. – № 23 (24). – С. 1–32.
8. Брызгалов А. А. Применение концепции «нулевого доверия» для защиты коммерческой тайны на предприятии в условиях
цифровизации / А. А. Брызгалов, П. А. Козырев, В. В. Ульянов // Вызовы цифровой экономики: технологический суверенитет
и экономическая безопасность. – Брянск: ФГБОУ ВО «Брянский государственный инженерно-технологический университет»
Инженерно–экономический институт, 2023. – С. 70–77.
9. Букирева Ю. М. Стратегия доступа к корпоративным сетям с применением модели нулевого доверия // Инновационные технологии: теория, инструменты, практика. – 2021. – №1. – С. 136–141.
10. Security of Zero Trust Networks in Cloud Computing: A Comparative Review / S. Sarkar, G. Choudhary, Sh. K. Shandilya, A. Hussain, H. Kim // Sustainability. – 2022. – №14. – С. 1–22.
11. Atencia M. Trust in networks of ontologies and alignments / M. Atencia, M. Al-Bakri, M.-C. Rousset // Knowledge and Information Systems. — 2013. — № 2 (42). — С. 1–27.
12. W. Al-shadood Enhancement the Security by Creating Ontology-Based Trust Management Using Semantic Web Tools // AlKadhum Journal of Science. — 2023. — № 2 (1). — С. 11–16.
13. Implementation of a Multi-Approach Fake News Detector and of a Trust Management Model for News Sources / C. Marche, I. Cabiddu, C. G. Castangia, L. Serreli // IEEE Transactions on Services Computing. – 2023. – № 6 (16). – С. 1–14.
14. Ан В. Р. Разработка алгоритма проведения аудита кибербезопасности / В. Р. Ан, В. А. Табакаева // МНСК-2021. Информационные технологии: материалы 59-й Международной научной студенческой конференции, Новосибирск, 12–23 апреля 2021 г. – Новосибирск, 2021. – С. 5. – EDN CAYHXE.
15. Макаренко С. И. Критерии и показатели оценки качества тестирования на проникновение // Вопросы кибербезопасности. –
2021. – №3 (43). – С. 43–57. DOI:10.681/2311-3456-2021-3-43-57
16. Ситская А. В. Вопросы аудита информационной безопасности / А. В. Ситская, В. В. Селифанов, П. А. Звягинцева // Безопасность цифровых технологий. – 2023. – № 3 (110). – С. 67–82.
17. Захахатнов В. Г. Функция желательности Харрингтона как критерий оптимального выбора зерносушилки / В. Г. Захахатнов, В. М. Попов, В. А. Афонькина // Известия Оренбургского государственного аграрного университета. – 2022. №2 (94). С. 110–114.

The purpose: to develop criteria for information security risk acceptance for an asset-based approach (ISO/IEC 27005). Research methods: an analysis of documents with the participation of the FSTEC of Russia was made, the criteria for information security risk acceptance (IS) defined in the ISO/IEC 27005 standard were studied, taking into account the requirements of GOST R ISO/IEC 27001. Based on the International Auditing Standard 320, recommendations are given for calculating the level of materiality of information security, which should become the basis for the development of information security risk criteria. The results: The criteria for risk acceptance for all business entities should be based on the principle of materiality, which is: 1% of total assets; 1% of revenue or total expenses (budget for the year); 5% of profit (for commercial organizations). The materiality indicator can be calculated for any organization, including budget organizations, where there is an asset value indicator or a consolidated budget for the year. The obtained conclusions allow us to obtain an estimated scale of information security risk acceptance in monetary terms. The novelty of the research: the study suggests the integration of economic aspects into the process of assessing information security risk criteria, which allows organizations to make informed decisions about the acceptability of risks, justify the budget of information security, and develop a feasibility study of information security projects. The monetary risk criteria of the IB will allow the implementation of the ISO/IEC 27005 assetbased approach. Contribution: Kozyr N. S. - the general concept of the study, structuring, description of the results, conclusions. Makaryan A. S. - systematization of regulatory and legal documentation in the field of information security risks (ISO/IEC 27005, Methodological documents and Orders of the Federal State Technical Committee); Oganesyan L. L. - economic aspects of information security risk (GOST R ISO/IEC 27001, ISA 320).
Keywords: information security risk criteria, information security materiality level, information security
economics, information security risk economics, information security management system, information security risk
management, information security, information security risk assessment, information security risks.

1. Козырь Н. С., Оганесян Л. Л. Экономические аспекты информационной безопасности. – Москва: ЮРАЙТ, 2023. 131 с.
2. Razikin Kh., Soewito B. Cybersecurity decision support model to designing information technology security system based on risk analysis and cybersecurity framework // Egyptian Informatics Journal. 2022. Vol. 23. No 3. P. 383-404. DOI 10.1016/j.eij.2022.03.001.
3. Schmid M., Pape S. Aggregating corporate information security maturity levels of different assets // IFIP Advances in Information and Communication Technology. 2020. Vol. 576. P. 376-392. DOI: 10.1007/978-3-030-42504-3_24.
4. Маслова М А. Научно-методические рекомендации по регулированию рисков нарушения информационной безопасности //
Информация и безопасность. 2022. Т. 25. № 4. С. 513–520. DOI 10.36622/VSTU.2022.25.4.005.
5. Волкова Л. В., Макарова Д. В., Докучаев В. А. Использование метода CRAMM для оценки информационных рисков //
Телекоммуникации и информационные технологии. 2021. Т. 8. № 1. С. 103–109.
6. Кортнев К. Методики управления рисками информационной безопасности и их оценки (часть 1, 14.05.2018) [электронный
ресурс]. Режим доступа: https://safe-surf.ru/specialists/article/5193/587932/ (дата обращения 16.10.2023).
7. Кортнев К. Методики управления рисками информационной безопасности и их оценки (часть 2, 22.05.2018) [электронный
ресурс]. Режим доступа: https://safe-surf.ru/specialists/article/5194/587935/?sphrase_id=45664 (дата обращения 16.10.2023).
8. Повышев А. А., Соколов А. Н., Мищенко Е. Ю. Универсальная классификация угроз безопасности информации и её применение для разработки модели угроз и оценки рисков // Вестник УрФО. Безопасность в информационной сфере. 2023. № 3(49). С. 68-80. DOI 10.14529/secur230307.
9. Баранова Е. К., Мурзакова А. А., Мурзакова Е. А. Сравнительный анализ программного обеспечения для анализа рисков
информационной безопасности в соответствии с ГОСТ Р ИСО/МЭК 27005-10 // Информационные технологии и вычислительные
системы. 2019. № 2. С. 75–83. DOI 10.14357/20718632190208.
10. Касперская Н. И. Анализ больших данных в ИБ предприятий. Перспективы развития // Защита информации. Инсайд. 2019.
№ 3(87). С. 34–43.
11. Путято М. М., Макарян А. С. Подходы к построению адаптивной системы защиты на основе корреляционного анализа
статистических характеристик инцидентов информационной безопасности // Электронный сетевой политематический журнал
«Научные труды КубГТУ». 2022. № 2. С. 148–162.
12. Козырь Н. С. Методические подходы риск-менеджмента информационной безопасности // Электронный сетевой политематический журнал «Научные труды КубГТУ». 2023. № 4. С. 99–109.

The purpose of research: Study the impact of adversarial attacks on the evaluation metrics of regression ML models. The methods of research: Emulation of signal propagation data in MIMO systems, synthesis of adversarial samples, execution of adversarial attacks on machine learning models, training of binary classifiers to detect adversarial anomalies in data. Scientific novelty: methods for performing adversarial attacks on a regression model for the problem of predicting the combined losses of the signal propagation path from the base station to end users in the emulated segment of the latest generation wireless networks have been studied. The result of research: Scenario generation and exploratory analysis of a dataset using the DeepMIMO emulator carried out. An adversarial attack with gradient sign maximization using the FGSM method was performed. An experimental comparison of binary classifiers for detecting malicious data was performed. An analysis of the dynamics of changes in the evaluation metrics of a regression model was performed in a scenario without adversarial attacks, a scenario under adversarial attack, and a scenario with isolating compromised data. Performing an adversarial FGSM attack with gradient sign maximization increases the value of the MSE metric by an average of 33% and reduces the value of the R2 metric by an average of 10%. The LightGBM binary classifier successfully detects records with adversarial anomalies in tabular data with 98% accuracy. Regression-based machine learning models are vulnerable to adversarial attacks, but timely intelligent analysis of network traffic and data transmitted over the network can detect malicious network activity.
Keywords:  adversarial attacks, wireless ad hoc networks, machine learning, regression, MIMO.

1. Петров И. А. Безопасность физического уровня для сетей 5G/6G // Вопросы кибербезопасности. – 2023. – №. 3. – С. 55.
2. Котенко И. В. и др. Атаки и методы защиты в системах машинного обучения: анализ современных исследований // Вопросы кибербезопасности. – 2024. – №. 1. – С. 59.
3. Gupta K. et al. An adversarial attacker for neural networks in regression problems // IJCAI Workshop on Artificial Intelligence Safety (AI Safety). – 2021.
4. Ribeiro A. H., Schön T. B. Overparameterized linear regression under adversarial attacks // IEEE Transactions on Signal Processing. – 2023. – V. 71. – P. 601–614.
5. Li F., Lai L., Cui S. On the adversarial robustness of linear regression // 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing (MLSP). – IEEE, 2020. – P. 1–6.
6. Mode G. R., Hoque K. A. Adversarial examples in deep learning for multivariate time series regression // 2020 IEEE Applied Imagery Pattern Recognition Workshop (AIPR). – IEEE, 2020. – P. 1–10.
7. Kong X., Ge Z. Adversarial Attacks on Regression Systems via Gradient Optimization // IEEE Transactions on Systems, Man, and Cybernetics: Systems. – 2023.
8. Meng L. et al. White-box target attack for EEG-based BCI regression problems // Neural Information Processing: 26th International Conference, ICONIP 2019, Sydney, NSW, Australia, December 12–15, 2019, Proceedings, Part I 26. – Springer International Publishing, 2019. – P. 476–488.
9. Santana E. J. et al. Detecting and mitigating adversarial examples in regression tasks: A photovoltaic power generation forecasting case study // Information. – 2021. – V. 12. – №. 10. – P. 394.
10. Balda E. R., Behboodi A., Mathar R. Perturbation analysis of learning algorithms: Generation of adversarial examples from classification to regression // IEEE Transactions on Signal Processing. – 2019. – V. 67. – №. 23. – P. 6078–6091.
11. Zhao P., Wan Z. Robust nonparametric regression under poisoning attack // Proceedings of the AAAI Conference on Artificial Intelligence. – 2024. – V. 38. – №. 15. – P. 17007–17015.
12. Deng Y. et al. An analysis of adversarial attacks and defenses on autonomous driving models // 2020 IEEE international conference on pervasive computing and communications (PerCom). – IEEE, 2020. – P. 1–10.
13. Костогрызов А. И., Нистратов А. А. Анализ угроз злоумышленной модификации модели машинного обучения для систем с искусственным интеллектом // Вопросы кибербезопасности. – 2023. – №. 5. – С. 9.
14. Ballet V. et al. Imperceptible adversarial attacks on tabular data // arXiv preprint arXiv:1911.03274. – 2019. DOI: https://doi.org/10.48550/arXiv.1911.03274
15. Alkhateeb A. DeepMIMO: A generic deep learning dataset for millimeter wave and massive MIMO applications // arXiv preprint arXiv:1902.06435. – 2019. DOI: https://doi.org/10.48550/arXiv.1902.06435

The purpose of research: the development of methodological, algorithmic and software for the creation of automated software generation tools based on large language models Research methods: analysis of architecture, methods and means of creating, teaching and applying large language models, research of methods and algorithms for fine-tuning and applying large language models to generate program code, experimental studies of developed algorithms and programs on the stand. The results obtained: the architectural and technological foundations of the construction and functioning of large language models (LLM) are investigated. Promising technologies, methods and tools for teaching and fine-tuning LLM to solve programming problems have been identified. A methodology has been developed for creating automated software code generation tools by implementing an iterative procedure for configuring a limited number of significant parameters of the basic LLM on specially prepared training datasets. The key modules and parameters of the LLM setup procedure are defined. Fragments of the software implementation of the technique in the Pytorch environment are presented. The results obtained during the experiments indicate the expediency of using this approach to develop automated software code generation tools. Scientific and practical significance: it consists in the development of methodological, algorithmic and software designed to create, with limited computing resources, models of automatic means of generating and testing software code based on large languages models, in which there is no catastrophic forgetting, the risk of retraining, hallucinations.
Keywords: large language models, deep learning, neural network models, transformer, Large Language
Model, self-attention.

1. A Survey of Large Language Models. Wayne Xin Zhao, Kun Zhou, Junyi Li et al. arXiv:2303.18223v13 [cs.CL] 24 Nov 2023.
2. Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning https://arXiv:2303.15647v1 [cs.CL] 28 Mar 2023.
3. Ankit Yadav, Mayank Singh. Boldly Going Where No Benchmark Has Gone Before: Exposing Bias and Shortcomings in Code Generation Evaluation. arXiv:2401.03855v2 [cs.CL] 23 Feb 2024.
4. Attention Is All You Need. Ashish Vaswani, Noam Shazeer, Niki Parmar. arXiv:1706.03762v7 [cs.CL] 2 Aug 2023
5. Jay Alammar. The Illustrated Transformer. http://jalammar.github.io/illustrated-transformer.
6. Jinjie Ni, Rui Mao, Zonglin Yang. Finding the Pillars of Strength for Multi-Head Attention. arXiv:2305.14380v2 [cs.LG] 15 Oct 2023. 
7. David Chiang, Alexander M. Rush, and Boaz Barak. 2021. Named tensor notation. ArXiv,abs/2102.13196.
8. Noam Shazeer. GLU Variants Improve Transformer. arXiv:2401.03065v1 [cs.SE] 5 Jan 2024.
9. LORA: Low-Rank adaptation of large language models. Edward Hu, Yelong Shen, Phillip Wallis and etl., arXiv:2106.09685v2 [cs.CL] 16 Oct 2021.
10. LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention. Renrui Zhang, Jiaming Han, Chris Liu, Peng Gao. arXiv:2303.16199v2 [cs.CV] 14 Jun 2023
11. Delta tuning: A comprehensive study of parameter efficient methods for pre-trained language models. Ning Ding, Yujia Qin, Guang Yang, Fu Wei, et al. ArXiv, abs/2203.06904
12. QLoRA: Quantization-aware low-rank adaptation of large language models Yuhui Xu Lingxi Xie Xiaotao Gu Xin Chen Heng Chang arXiv:2309.14717v2 [cs.LG] 9 Oct 2023.
13. QDyLoRA: Quantized Dynamic Low-Rank Adaptation for Efficient Large Language Model Tuning Hossein Rajabzadeh12, Mojtaba Valipour 1, Tianshu Zhu 2, Marzieh Tahaei arXiv:2402.10462v1 [cs.LG] 16 Feb 2024
14. Llama 2: Open Foundation and Fine-Tuned Chat Models. Hugo Touvron, Louis Martin, Kevin Stone and et al. arXiv:2307.09288v2 [cs.CL] 19 Jul 2023.
15. Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models M. Weyssow, Xin Zhou, K. Kim et al. arXiv:2308.10462v2 [cs.SE] 18 Jan 2024.
16. CodePori: Large Scale Model for Autonomous Software Development by Using Multi-Agents. Zeeshan Rasheed, Muhammad Waseem, Mika Saari, Pekka Abrahamsson et al. arXiv:2402.01411v1 [cs.SE] 2 Feb 2024.
17. CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution. Alex Gu, Baptiste Roziere, Hugh Leather et al. arXiv:2401.03065v1 [cs.SE] 5 Jan 2024.
18. MultiPL-E: A Scalable and Polyglot Approach to Benchmarking Neural Code Generation. Federico Cassano, John Gouwar, Daniel Nguyen et al. IEEE TRANSACTIONS ON SOFTWARE ENGINEERING, VOL. 49, NO. 7, JULY 2023.
19. OOP: Object-Oriented Programming Evaluation Benchmark for Large Language Model. Shuai Wang, Liang Ding, Li Shen et al. arXiv:2401.06628v2 [cs.CL] 21 Feb 2024.
20. Mixtral of Experts. Albert Q. Jiang, Alexandre Sablayrolles, Antoine Roux. et al. arXiv:2401.04088v1 [cs.LG] 8 Jan 2024.

The purpose of the study: development and experimental study of a method for identifying facts of circumvention of traffic blocking, providing access to prohibited Internet resources. Research methods: system analysis, theory of metric spaces, mathematical statistics, theory of artificial intelligence systems, theory of experimental data processing. The results obtained: the informative signs used by current methods and means of blocking prohibited Internet resources, as well as ways to circumvent such locks, are systematized; a new set of informative signs providing a solution to the research problem is determined; a generalized method for detecting facts of circumventing the blocking of prohibited Internet resources is proposed and experimental confirmation of its productivity is obtained. The scientific novelty of the results obtained is determined by the systematization of regulatory and organizational and technical requirements for means of detecting and blocking access to prohibited Internet resources, which ensures the formation of forecasts for their development; using the author's set of traffic monitoring methods based on the analysis of digital fingerprints of communication protocols and patterns of sequence and volume of transmitted data, providing the possibility of identifying and analyzing informative signs usually hidden to a passive observer; the development of a generalized method for detecting the fact of bypassing traffic blocking based on the analysis of stable patterns inherent in communication sessions. Contribution of the authors: Begaev A. N. - definition of technical and economic limitations and requirements for the implementation of the method of detecting the fact of bypassing traffic blocking; Komarov I. I. - setting the task and defining the research plan; Ishkuvatov S. M. - analysis of informative signs, development of a method for detecting the fact of bypassing traffic blocking, conducting an experiment; Levko I. V. - analysis of regulatory aspects of regulating access to Internet resources, analysis and interpretation of experimental results.
Keywords:  Internet censorship, traffic filtering, traffic tunneling, session masking, passive observer, digital
fingerprint, deep packet analysis.

1. Чеповский А. А. Об особенностях построения и анализа графов взаимодействующих объектов в сети telegram-каналов // Вопросы кибербезопасности. – 2022. – №. 1 (53), с. 75–81. DOI:10.21681/2311-3456-2022-2-75-81
2. Капицын С. Ю., Рюмшин К. Ю., Вареница В. В. Логико-лингвистический механизм формирования «бумажных» пуль при информационном противоборстве // Вопросы кибербезопасности. – 2022. №. 1 (53), с. 93–99. DOI:10.21681/2311-3456-2022-1-93-99
3. Новикова Е. С. и др. Обнаружение вторжений на основе федеративного обучения: архитектура системы и эксперименты //
Вопросы кибербезопасности. – 2023. – № 6 (58), с. 50–66. DOI:10.21681/2311-3456-2023-6-50-66
4. Коноваленко С. А. Методика оценивания информационной устойчивости гетерогенной системы обнаружения компьютерных
атак // Вопросы кибербезопасности. – 2023. – №. 6 (58), с. 67–80. DOI:10.21681/2311-3456-2023-6-67-80
5. Шадрина А. Д. Способы защиты информации в веб-приложении // Программно-техническое обеспечение автоматизированных
систем. – 2021. – с. 116–119.
6. Гурина Л. А., Айзенберг Н. И. Поиск эффективного решения по обеспечению защиты от киберугроз сообщества микросетей со взаимосвязанными информационными системами // Вопросы кибербезопасности. – 2023. – №. 3 (55). – с. 37–49.
DOI:10.21681/2311-3456-2023-3-37-49
7. Павленко Е. Ю. и др. Распознавание киберугроз на адаптивную сетевую топологию крупномасштабных систем на основе рекуррентной нейронной сети // Вопросы кибербезопасности. – 2022. – №. 6 (52), с. 93–99. z DOI:10.21681/2311-3456-2022-6-93-99
8. Добродеев А. Ю. Кибербезопасность в Российской Федерации. Модный термин или приоритетное технологическое направление
обеспечения национальной и международной безопасности XXI века // Вопросы кибербезопасности. – 2021. – №. 4 (44). –
С. 61–72. DOI:10.21681/2311-3456-2021-4-61-72
9. Карцхия А. А. Новые элементы национальной безопасности: национальный и международный аспект // Вопросы кибербезопасности. – 2020. – №. 6 (40). – С. 72–82. DOI:10.21681/2311-3456-2020-6-72-82
10. VAS Experts. СКАТ – Система контроля и анализа трафика. VAS Experts. URL: https://vasexperts.ru/wp-content/uploads/2022/07/filtracziya-po-spiskam-rkn-i-minyusta.pdf (дата обращения: 10.02.2024)
11. Ишкуватов С. М., Швед В. Г., Филькова И. А. Метод оценки близости цифровых отпечатков реализаций протоколов // Защита информации. Инсайд. – №. 2. – с. 29–33.
12. Ишкуватов С. М., Комаров И. И. Анализ аутентичности трафика на основании данных цифровых отпечатков реализаций сетевых протоколов // Научно-технический вестник информационных технологий, механики и оптики. – 2020. – Т. 20. – №. 5. – С. 747–754.
13. Ишкуватов С. М., Бегаев А. Н., Комаров И. И. Метод автоматической классификации цифровых отпечатков TLS-протокола // Вопросы кибербезопасности. – 2024. – №. 1 (59), с. 67–74. DOI:10.21681/2311-3456-2024-1-67-74
14. Henning Schulzrinne, Stephen Casner, Ron Frederick, Van Jacobson. RTP: A transport protocol for real-time applications. RFC 3550. 2003 г.
15. Ali Rasteh, Florian Delpech, Carlos Aguilar-Melchor et al. Encrypted internet traffic classification using a supervised spiking neural network. Neurocomputing. 2022 г., Т. 503., 8.
16. Gupta Neha, Jindal Vinita, Bedi Punam. Encrypted traffic classification using extreme gradient boosting algorithm. International  Conference on Innovative Computing and Communications. 2022 г., Т. Volume 3 / Springer., 9.
17. Islam Faiz Ul, Liu Guangjie, Liu Weiwei. Identifying VoIP traffic in VPN tunnel via flow spatio-temporal features. Mathematical Biosciences and Engineering. 2020 г., Т. 15, 5.
18. Ишкуватов, С. М. Способ и алгоритм определения типа трафика в шифрованном канале связи // Труды учебных заведений
связи. 2022 г., Т. 8, 4.

The aim of the work is to develop a method for detecting ransomware based on the analysis of sequences of API calls and system calls. The research method is the analysis of records in the behavioral report of the virtualization product using the deep learning algorithm DeBERTa-V3. The result obtained: despite the wide variety of families and variations of the ransomware family used by attackers in computer attacks, they all leave traces of their work in the attacked infrastructure. One of the ways to identify malicious software and prevent infection is to use the Sandbox technology, including to identify the hidden capabilities of the object under study and anomalies of its behavior. The functioning of any computer program can be represented as a set of records of its actions in a behavior report, which can be considered as signs of an object. The paper analyzes reports on the behavior of ransomware programs. Based on the generated data set using a deep learning algorithm, a model is built that allows further detection of malicious objects, and a method for detecting ransomware is described. The scientific novelty consists in the creation of a method for detecting ransomware based on the analysis of the behavioral report of an executable object using the deep learning algorithm DeBERTa-V3.
Keywords: malware, sandbox, deep learning, BERT, Ransomware, computer attacks.

1. Ijaz M., Durad M. H., Ismail M. Static and dynamic malware analysis using machine learning //2019 16th International bhurban conference on applied sciences and technology (IBCAST). – IEEE, 2019. – С. 687–691. http://dx.doi.org/10.1109/IBCAST.2019.8667136
2. Aboaoja F. A. et al. Malware detection issues, challenges, and future directions: A survey //Applied Sciences. – 2022. – Т. 12. – №. 17. – С. 8482.
3. Asghar H. J. et al. Use of cryptography in malware obfuscation //Journal of Computer Virology and Hacking Techniques. – 2024. – Т. 20. – №. 1. – С. 135–152.
4. Zhang X. et al. Android application forensics: A survey of obfuscation, obfuscation detection and deobfuscation techniques and their impact on investigations //Forensic Science International: Digital Investigation. – 2021. – Т. 39. – С. 301285.
5. Cheng B. et al. {Obfuscation-Resilient} Executable Payload Extraction From Packed Malware //30th USENIX Security Symposium (USENIX Security 21). – 2021. – С. 3451–3468
6. Brezinski K. et al. Metamorphic malware and obfuscation: a survey of techniques, variants, and generation kits //Security and Communication Networks. – 2021. – Т. 2023.
7. Alsmadi T., Alqudah N. A survey on malware detection techniques //2021 international conference on information technology (ICIT). – IEEE, 2021. – С. 371–376.
8. Aslan Ö. A., Samet R. A comprehensive review on malware detection approaches //IEEE access. – 2020. – Т. 8. – С. 6249–6271.
9. Maniriho P., Mahmood A. N., Chowdhury M. J. M. API-MalDetect: Automated malware detection framework for windows based on API calls and deep learning techniques //Journal of Network and Computer Applications. – 2023. – Т. 218. – С. 103704.
10. Sun J. et al. Categorizing malware via A Word2Vec-based temporal convolutional network scheme //Journal of Cloud Computing. – 2020. – Т. 9. – С. 1–14.
11. Chandak A., Lee W., Stamp M. A comparison of word2vec, hmm2vec, and pca2vec for malware classification //Malware analysis using artificial intelligence and deep learning. – 2021. – С. 287–320.
12. Yesir S., Soğukpinar İ. Malware detection and classification using fasttext and bert //2021 9th International Symposium on Digital Forensics and Security (ISDFS). – IEEE, 2021. – С. 1–6.
13. Pandya V. Contextualized Vector Embeddings for Malware Detection. – 2022. https://doi.org/10.31979/etd.rjra-9c8m
14. Rahali A., Akhloufi M. A. Malbert: Malware detection using bidirectional encoder representations from transformers //2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC). – IEEE – 2021. – С. 3226–3231.
15. Rahali A., Akhloufi M. A. MalBERTv2: Code Aware BERT-Based Model for Malware Identification //Big Data and Cognitive Computing. – 2023. – Т. 7. – №. 2. – С. 60.
16. He P., Gao J., Chen W. Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing // arXiv preprint arXiv:2111.09543. – 2021.
17. Devlin J. et al. Bert: Pre-training of deep bidirectional transformers for language understanding //arXiv preprint arXiv:1810.04805. – 2018.
18. Kingma D. P., Ba J. Adam: A method for stochastic optimization //arXiv preprint arXiv:1412.6980. – 2014.

The goal of the investigation: conceptual counteraction to software vulnerabilities. Research methods: system analysis, modeling, synthesis of solutions.
Results: in the second part of the article, an analytical model is proposed that formalizes the essence and relationship of the ontological model of the software domain with vulnerabilities. The influence of the entities of the subject area on the feasibility of directions in it (software engineering, introduction of vulnerabilities and their neutralization) was assessed, which made it possible to synthesize conceptual ways to counter vulnerabilities. The scientific novelty of the work is determined by the complete formalization of objects and subjects of the subject area, as well as their relationships.
Keywords: information security, vulnerability, counteraction, analytical model, conceptual solutions.

1. Леонов Н. В. Противодействие уязвимостям программного обеспечения. Часть 1. Онтологическая модель // Вопросы кибербезопасности. № 2(60). 2024. DOI: 10.21681/2311-3456-2024-2-87-92
2. Миронов С. В., Батраева И. А., Дунаев П. Д. Библиотека для разработки компиляторов // Труды Института системного программирования РАН. 2022. Т. 34. № 5. С. 77–88. DOI: 10.15514/ISPRAS-2022-34(5)-5.
3. Афонин М. В. Компиляция. Сборка и связывание проектов // Инновационный потенциал развития общества: взгляд молодых
ученых: сборник научных статей 3-й Всероссийской научной конференции перспективных разработок (Курск, 01 декабря 2022
года). Том 3. 2022. С. 115–118.
4. Якимук А. Ю., Устинов С. А., Лазарев Т. П., Коваленко А. С. Методы формализации описания сценариев кибератак // Электронные средства и системы управления. Материалы докладов Международной научно-практической конференции. 2022. № 1–2. С. 73–76.
5. Суздалов Д. В., Некрасов А. Н. Разработка сканера уязвимостей // Наука молодых: сборник материалов Межрегиональной молодежной научной конференции, посвященной памяти Ф. А. Бабушкина, (Сыктывкар, 25–26 мая 2023 года). 2023. С. 139–143.
6. Вареница В. В., Марков А. С., Савченко В. В., Цирлов В. Л. Практические аспекты выявления уязвимостей при проведении сертификационных испытаний программных средств защиты информации // Вопросы кибербезопасности. 2021. № 5 (45). С. 36–44. DOI: 10.21681/2311-3456-2021-5-36-44.
7. Израилов К. Е. Методология реверс-инжиниринга машинного кода. Часть 2. Статическое исследование. Труды учебных заведений связи // 2023. Т. 9. № 6. С. 68–82. DOI: 10.31854/1813-324X-2023-9-6-68-82.
8. Коржев А. А. Обеспечение безопасности программного обеспечения // Стратегическое развитие инновационного потенциала
отраслей, комплексов и организаций: сборник статей XI Международной научно-практической конференции (Пенза, 10–11 октября 2023 года). 2023. – С. 237–241.
9. Градский Д. Ю. Методы обфускации кода // Оригинальные исследования. 2020. Т. 10. № 5. С. 177–180.
10. Иванов М. А., Коннова И. Г., Саликов Е. А., Степанова М. А. Обфускация логических схем генераторов псевдослучайных чисел на регистрах сдвига с линейными и нелинейными обратными связями // Безопасность информационных технологий. 2021.
Т. 28. № 1. С. 74–83. DOI: 10.26583/bit.2021.1.06.
11. Лукацкий А. В. Обзор мировых трендов по промышленной кибербезопасности // Релейщик. 2020. № 1 (36). С. 60–62.
12. Ерохин В. В., Притчина Л. С. Анализ и совершенствование методов обнаружения шелл-кодов (shellcode) в компьютерных системах // Прикладная информатика. 2021. Т. 16. № 2 (92). С. 103–122.
13. Руднев Н. О., Герасимова В. Ф., Шагапов И. А. Метод закрепления доступа в системе посредством инъекции кода в операционной системе Windows // Естественные и технические науки. 2022. № 12 (175). С. 398–403.
14. Нефедов В. В. Методы внедрения кода в исполняемые файлы PE-формата // Молодежная научная школа кафедры «Защищенные
системы связи». 2021. Т. 1. № 2 (4). С. 61–68.
15. Маркин Д. О., Макеев С. М. Система защиты терминальных программ от анализа на основе виртуализации исполняемого кода // Вопросы кибербезопасности. 2020. № 1 (35). С. 29–41. DOI: 10.21681/2311-3456-2020-01-29-41.
16. Буйневич М. В., Ганов Г. А., Израилов К. Е. Интеллектуальный метод визуализации взаимодействий программ в интересах аудита информационной безопасности операционной системы // Информатизация и связь. 2020. № 4. С. 67–74.
17. Фомин А. И. Оценка сложности исследования дизассемблированного кода исполняемых программ // Естественные и технические науки. 2021. № 7 (158). С. 210–211

The key management subsystem main function of a telecommunication system in the key compromises context by an intruder is to ensure cryptographic connectivity timely restoration of geographically dispersed correspondents via secure channels, which is updated for network correspondents, due to the fact that the resistance of the network key to compromise is minimal. The study purpose is to find ways to reduce the recovery time of network crypto-connectivity. The research method is the introduction into information theory of the coefficient of asymptotic gain in time of network key agreement under conditions of an unlimited increase in the length of the transmitted sequence and specified requirements for an openly generated key of a communication network. Research results - two models of open key generation are investigated. In the first model, keys are initially generated in turn in each channel of the communication network, and then one of the correspondents selects one of the keys as a network key and transmits it through private channels to other correspondents. In the second, the key is formed simultaneously along the constituent channels of the network. Therefore, a coefficient of asymptotic gain in the time of key formation of three network correspondents is introduced, which is a determining indicator of open network key agreement asymptotic efficiency. An assessment of the efficiency indicator was carried out, which made it possible to find the preferential information-theoretic conditions for using each of the models. Practical value - the results can be useful to researchers for analyzing various information security subsystems of telecommunication systems to assess the potential for reducing the recovery time of crypto-connectivity.
Keywords:  information theory; communication network; intruder; network key; open network key negotiation;
key throughput; coefficient of asymptotic gain in the time of network key formation.

1. Синюк А. Д., Тарасов А. А., Остроумов О. А. Метод оценки временной эффективности передачи информации дискретного широковещательного канала связи // Телекоммуникации. 2021. № 7. С. 10–17. DOI: 10.31044/1684-2588-2021-0-7-10-17. EDN JMFKNS.
2. Синюк А. Д., Остроумов, О. А. Оценка ключевой пропускной способности сети связи // Вестник компьютерных и информационных технологий. 2020. Т. 17. № 11(197). С. 47–54. DOI: 10.14489/vkit.2020.11. Pp. 047–054.
3. Zhang Qikun, Li Yongjiao, Gan Yong, Zheng Chuanyang, Luo Xiangyang, Zheng Jun Group Key Agreement Protocol Based on Privacy Protection and Attribute Authentication // IEEE Access. Volume: 7. Page(s): 87085–87096. DOI: 10.1109/ACCESS.2019.2926404.
4. Pinar Sen, Sung Hoon Lim, Young-Han Kim On the Optimal Achievable Rates for Linear Computation With Random Homologous Codes // IEEE Transactions on Information Theory (Volume: 66), Issue: 10, October 2020) Page(s): 6200–6221 Date of Publication: 20 July 2020 DOI: 10.1109/TIT.2020.3010253
5. Hongchao Zhou, Abbas El Gamal Network Information Theoretic Security with Omnipresent Eavesdropping // IEEE Transactions on Information Theory. Volume: 67. Issue: 12. December 2021. Page(s): 8280–8299. DOI: 10.1109/TIT.2021.3116962.
6. Onur Günlü, Rafael F. Schaefer, Holger Boche, H. Vincent Poor Secure and Private Distributed Source Coding With Private Keys and Decoder Side Information // IEEE Transactions on Information Forensics and Security (Volume: 18) Page(s): 3803–3816 Date of Publication: 14 June 2023. DOI: 10.1109/TIFS.2023.3286285
7. Tetsunao Matsuta; Tomohiko Uyematsu Coding Theorems for Asynchronous Slepian-Wolf Coding Systems // IEEE Transactions on Information Theory (Volume: 66), Issue: 8, August 2020), Page(s): 4774–4795, Date of Publication: 18 February 2020, ISSN Information: Print ISSN: 0018-9448 Electronic ISSN: 1557-9654, DOI: 10.1109/TIT.2020.2974736
8. Matthieu Bloch, Onur Günlü, Aylin Yener, Frédérique Oggier, H. Vincent Poor, Lalitha Sankar, Rafael F. Schaefer An Overview of Information-Theoretic Security and Privacy: Metrics, Limits and Applications // IEEE Journal on Selected Areas in Information Theory. Volume: 2. Issue: 1. March 2021. Page(s): 5–22. DOI: 10.1109/JSAIT.2021.3062755.
9. Остроумов О. А., Синюк А. Д. Пропускная способность широковещательного канала связи // Вестник компьютерных
и информационных технологий. 2019. № 9 (183). С. 33–42. DOI: 10.14489/vkit.2019.09.pp.033-042.
10. Cheuk Ting Li; Venkat Anantharam One-Shot Variable-Length Secret Key Agreement Approaching Mutual Information // IEEE Transactions on Information Theory (Volume: 67), Issue: 8, August 2021) Page(s): 5509–5525 at of Publication: 09 June 2021 DOI: 10.1109/TIT.2021.3087963
11. Zhang Qikun, Li Yongjiao, Gan Yong, Zheng Chuanyang, Luo Xiangyang, Zheng Jun Group Key Agreement Protocol Based on Privacy Protection and Attribute Authentication // IEEE Access. Volume: 7. Page(s): 87085–87096. Date of Publication: 02 July 2019 Electronic ISSN: 2169-3536 INSPEC Accession Number: 18826825. DOI: 10.1109/ACCESS.2019.2926404.
12. Vamoua Yachongka, Hideki Yagi, Hideki Ochiai Key Agreement Using Physical Identifiers for Degraded and Less Noisy Authentication Channels // IEEE Transactions on Information Forensics and Security (Volume: 18) Page(s): 5316 – 5331, Date of Publication: 23 August 2023 DOI: 10.1109/TIFS.2023.3307976
13. Onur Günlü;Rafael F. Schaefer Controllable Key Agreement With Correlated Noise // IEEE Journal on Selected Areas in Information Theory ( Volume: 2, Issue: 1, March 2021) Page(s): 82–94 Date of Publication: 25 January 2021 Electronic ISSN: 2641-8770 DOI: 10.1109/JSAIT.2021.3054035
14. Mohamed Nafea, Aylin Yener Generalizing Multiple Access Wiretap and Wiretap II Channel Models: Achievable Rates and Cost of Strong Secrecy // IEEE Transactions on Information Theory. Volume: 65. Issue: 8. August 2019. Page(s): 5125 – 5143. DOI: 10.1109/TIT.2019.2908832.
15. Остроумов О. А., Синюк А. Д. Информационная скорость формирования сетевого ключа по открытым виртуальным каналам
связи // Вопросы кибербезопасности. 2023. № 3(55). с. 78–89. DOI: 10.21681/2311-3456-2023-3-78-89.
16. Anuran Makur Coding Theorems for Noisy Permutation Channels // IEEE Transactions on Information Theory (Volume: 66, Issue: 11, November 2020) Page(s): 6723–6748 Date of Publication: 16 July 2020. DOI: 10.1109/TIT.2020.3009468
17. Haoheng Yuan, Yanghe Feng, Chuanchuan Yang, Zhuojun Zhuang, Bin Dai Two-User Gaussian Broadcast Wiretap Channel With Common Message and Feedback: Revisit // IEEE Transactions on Information Forensics and Security (Volume: 19) Page(s): 178–193 Date of Publication: 25 September 2023. DOI: 0.1109/TIFS.2023.3318948
18. Meryem Benammar, Pablo Piantanida, Shlomo Shamai on the Compound Broadcast Channel: Multiple Description Coding and Interference Decoding // IEEE Transactions on Information Theory (Volume: 66). Issue: 1, January 2020) Page(s): 38–64 Date of Publication: 23 September 2019. DOI: 10.1109/TIT.2019.2942615
19. Alejandro Cohen, Rafael G. L. D’Oliveira, Salman Salamatian, Muriel Médard Network Coding-Based Post-Quantum Cryptography // IEEE Journal on Selected Areas in Information Theory ( Volume: 2, Issue: 1, March 2021) Page(s): 49 – 64 Date of Publication: 26 January 2021 Electronic ISSN: 2641-8770. DOI: 10.1109/JSAIT.2021.3054598
20. Cheuk Ting Li, Venkat Anantharam One-Shot Variable-Length Secret Key Agreement Approaching Mutual Information // IEEE Transactions on Information Theory. Volume: 67. Issue: 8. August 2021. Page(s): 5509–5525. DOI: 10.1109/TIT.2021.3087963.
21. Vidhi Rana, Rémi A. Chou, Hyuck M. Kwon Information-Theoretic Secret Sharing From Correlated Gaussian Random Variables and Public Communication // IEEE Transactions on Information Theory (Volume: 68), Issue: 1, January 2022) Page(s): 549–559 Date of Publication: 27 October 2021. DOI: 0.1109/TIT.2021.3122808
22. Starostin V., Korzhik V., Kabardov M., Gerasimovich A., Yakovlev V., Morales-Luna G Key generation protocol executing through nonreciprocal fading channels // International Journal of Computer Science and Applications. 2019. Т. 16. № 1. С. 1–16.
23. Синюк А. Д., Тарасов А. А., Остроумов О. А. Теоретико-информационное представление виртуализации сетевого канала перехвата // Информатика и автоматизация. 2023. Т. 2. № 4. с. 721–744. DOI: 10.15622/ia.22.4.1.
24. Синюк А. Д., Остроумов О. А. Теорема о ключевой пропускной способности сети связи // Информационно-управляющие системы. 2018. № 5(96). с. 79–87. DOI: 10.31799/1684-8853-2018-5-79-87.
25. Amin Gohari, Onur Günlü, Gerhard Kramer Coding for Positive Rate in the Source Model Key Agreement Problem // IEEE Transactions on Information Theory. Volume: 66. Issue: 10. October 2020. Page(s): 6303–6323. DOI: 10.1109/TIT.2020.2990750.
26. Ignazio Pedone, Andrea Atzeni, Daniele Canavese, Antonio Lioy Toward a Complete Software Stack to Integrate Quantum Key Distribution in a Cloud Environment // IEEE Access (Volume: 9) Page(s): 115270–115291 Date of Publication: 03 August 2021 Electronic ISSN: 2169-3536 DOI: 10.1109/ACCESS.2021.3102313
27. Yi Luo; Hao-Kun Mao; Qiong Li; Nan Chen An Information-Theoretic Secure Group Authentication Scheme for Quantum Key Distribution Networks // IEEE Transactions on Communications (Volume: 71), Issue: 9, September 2023) Page(s): 5420–5431. Date of Publication: 29 May 2023. DOI: 10.1109/TCOMM.2023.3280561

The purpose of the study: comparison of a wide range of different models to construct graphs of interacting objects in a public Telegram channels network in order to identify among them the most suitable ones, in which the resulting graph is closest to scale-free networks.
Method: for the constructed weighted graphs, within the framework of each of the models under consideration, power laws are found that most closely approximate the empirical distributions of the obtained vertices weights, after which the quality of the resulting approximation is assessed.
Results: the article presents models to construct graphs that characterize the information impact in the Telegram channels network. This paper presents the results of a study of 180 cases - studies were conducted for 12 models on 15 data sets. As part of these studies, parameters of power laws that approximate empirical data were found. It is shown which of the models have these parameters that are not characteristic of scale-free networks. Using the Kolmogorov criterion, hypotheses about the nature of the distribution of the models were tested. Illustrations are provided to clearly show the results of the study. It is shown which of the models is best suited to construct graphs of interacting objects in a network of Telegram channels. Such graphs can subsequently be analyzed to identify key vertices. Scientific novelty: models are proposed to represent the interaction of objects in the Telegram channel network in the form of weighted graphs. The distribution of vertex weights in the resulting graphs of interacting objects has been researched. Studying this important property for weighted graphs obtained by importing data from real networks has yielded important theoretical and practical results. It was revealed that the UMR-model to construct such graphs has a property characteristic of scale-free networks.
Keywords: scale-free networks, model of information impact, community detection, analysis of social
networks, Kolmogorov goodness-of-fit test, power law distribution, vertex weight.

1. Fortunato, S., Newman, M. E. J. 20 years of network community detection // Nat. Phys. 2022. № 18. P. 848–850.
2. Чеповский А. А. О неявных сообществах на графе взаимодействующих объектов // Успехи кибернетики. 2023. Т.4. № 1.
C. 56–64.
3. Blöcker, C., Nieves, J. C. & Rosvall, M. Map equation centrality: community-aware centrality based on the map equation. // Appl Netw Sci. 2022. № 7:56. — 24 p. DOI: 10.1007/s41109-022-00477-9
4. Rajeh, S., Savonnet, M., Leclercq, E. et al. Comparative evaluation of community-aware centrality measures // Qual Quant. 2023. 57. P. 1273–1302. DOI: 10.1007/s11135-022-01416-7.
5. Попов В. А., Чеповский А. А. Модели импорта данных из мессенджера Telegram // Вестник Новосибирского государственного университета. Серия: Информационные технологии. 2022. Т.20. №2. С. 60–71.
6. Попов В. А., Чеповский А. А. Выделение неявных пересекающихся сообществ на графе взаимодействия Telegram-каналов
с помощью «метода Галактик» // Труды ИСА РАН. 2022. Т.72. №4. C. 39–50.
7. Чеповский А.А. Анализ графов взаимодействующих объектов. – М.: Национальный открытый университет «ИНТУИТ». 2022. – 270 с.
8. Щербакова, Н. Г. Модели сетей с предпочтительным присоединением // Проблемы информатики. 2019. № 3(44). С. 46–61.
9. Бадрызлов, В. А., Юдина М. Н. Исследование процессов распространения информации в социальной сети методом
имитационного моделирования / Десятая всероссийская научно-практическая конференция по имитационному моделированию
и его применению в науке и промышленности «Имитационное моделирование // Теория и практика» (ИММОД-2021): Труды
конференции, Санкт-Петербург, 20–22 октября 2021 года / Редакторы Плотников А. М., Долматов М. А., Смирнова Е. П. – СанктПетербург: АО «Центр технологии судостроения и судоремонта». 2021. С. 89–94.
10. Tereza Nečasová, Ninon Burgos, David Svoboda, Chapter 25 – Validation and evaluationmetrics for medical and biomedical image synthesis / Biomedical Image Synthesis and Simulation // Academic Press. 2022. P. 573–600. DOI: 10.1016/B978-0-12-824349-7.00032-3.

The aim of the work is to develop a generalized formal model for systematizing the main classifiers of destructive and constructive events in the infrastructure of the digital space of a sovereign state to organize the autonomy of an intelligent agent in the form of a data facet. Research method: using a syntactic representation of information theory data at the intersection of a model for managing complex systems and an information security model for formalization in the form of a conceptual model. Research result: a generalized model for systematizing classifiers of destructive and constructive events of an opposing system within the digital space of a sovereign state has been developed, which allows not only to use its own resources to predict attacks and eliminate destructive elements at the program level, but also to involve the digital image of the social environment as one of the main elements to solve problems. As a connecting link in the work, it is proposed to use intelligent botnet agents, the functionality of which involves not only shadow interaction with user workstations, but also work with the social environment directly. The resulting formulation solves the pressing problem of data formalization - modeling the processes of countering external destructive attacks with the distribution of functional tasks, which will allow us to reconsider the concept of our own security and increase the resistance of the digital environment to possible negative impacts. The scientific novelty lies in the development of a new element of conceptual modeling of destructors in the form of autonomous models - a facet-attributive process, which allows not only to adaptively change the rules of state transition, but also to modify one's own parametric indicators.
Keywords: destructor, modeling, intelligent agent, facet, hierarchy, transition rules, autonomy, digital space,
system.

1. Кевин Митник «Искусство обмана». – режим доступа: https://remarx.ru/media/books/ iskusstvo_obmana_mitnikpdf.pdf
2. Рыженко А. А. Умная бот-сеть или модель интеллектуального деструктора // Вопросы кибербезопасности. 2023. № 5(57).
С. 60–68. DOI: 10.21681/2311-3456-2023-5-60-68
3. Gibert, D., Mateu, C., Planes, J. et al. Using convolutional neural networks for classification of malware represented as images. J Comput Virol Hack Tech 15, 15-28 (2019). https://doi.org/10.1007/s11416-018-0323-0
4. Bernardeschi, C., Domenici, A. & Palmieri, M. Formalization and co-simulation of attacks on cyber-physical systems. J Comput Virol Hack Tech 16, 63-77 (2020). https://doi.org/10.1007/s11416-019-00344-9
5. Jain, M., Andreopoulos, W. & Stamp, M. Convolutional neural networks and extreme learning machines for malware classification. J Comput Virol Hack Tech 16, 229-244 (2020). https://doi.org/10.1007/s11416-020-00354-y
6. Rahman, R.U., Tomar, D.S. Threats of price scraping on e-commerce websites: attack model and its detection using neural network. J Comput Virol Hack Tech 17, 75-89 (2021). https://doi.org/10.1007/s11416-020-00368-6
7. Reddy, V., Kolli, N. & Balakrishnan, N. Malware detection and classification using community detection and social network analysis. J Comput Virol Hack Tech 17, 333-346 (2021). https://doi.org/10.1007/s11416-021-00387-x
8. Ebrahim, M., Golpayegani, S. A. H. Anomaly detection in business processes logs using social network analysis. J Comput Virol Hack Tech 18, 127-139 (2022). https://doi.org/10.1007/s11416-021-00398-8
9. Рыженко А. А., Рыженко Н. Ю. Интеллектуальные деструкторы и мобильные банковские клиенты / Актуальные проблемы
и перспективы развития экономики: Труды XXI Международной научно-практической конференции. Симферополь-Гурзуф,
20–22 октября 2022 год. / Под ред. д.э.н., д.пед.н., профессора Н. В. Апатовой. – Симферополь: Издательский дом КФУ
им. В. И. Вернадского, 2022. – с. 241-242.
10. Рыженко А. А. Модифицированный алгоритм вируса полиморфика как основа деструктора информационной среды / Информатика: проблемы, методология, технологии: сборник материалов XVIII международной научно-методической конференции: в 7 т. / под редакцией Н. А. Тюкачева; Воронеж, Воронежский государственный университет, 14-15 февраля 2019 г. – Воронеж:
Издательство «Научно-исследовательские публикации» (ООО «Вэлборн»), 2019. – Т. 5. – С. 857–861.
11. Рыженко А. А. Модель вложенной пирамиды системы управления безопасностью информационного пространства госкорпорации / Противодействие терроризму и экстремизму в информационных системах: сборник научных статей Всероссийской конференции – М.: Московский университет МВД России имени В. Я. Кикотя, 2020. – с. 65–69.
12. Рыженко А. А., Рыженко Н. Ю. Безопасность информации цифровой экономики / Актуальные проблемы и перспективы развития экономики. Труды Юбилейной XX Всероссийской с международным участием научно-практической конференции. Симферополь, 2021. С. 289–291.
13. Рыженко А. А. Фасетно-иерархическая модель как альтернатива существующим моделям систем поддержки управления /
Управление информационными ресурсами. Материалы XIX Международной научно-практической конференции. Минск, 2023.
С. 37-38
14. Любавский А. Ю. О необходимости развития алгоритмического мышления следователей в контексте расследования
киберпреступлений / Проблемы противодействия киберпреступности. Материалы международной научно-практической
конференции. Москва, 2023. – с. 105–108.
15. Любавский А. Ю. Актуальные вопросы обеспечения безопасности персональных данных в сети интернет / Обеспечение
информационной безопасности: вопросы теории и практики. Сборник статей Всероссийской научно-практической конференции.
Науч. редакторы Г. Г. Камалова, В. Г. Ившин, Г. А. Решетникова. Ижевск, 2023. – с. 39–45.

The goal of article: the creation of a methodology for identifying the author of textual information, including natural language texts and program source codes, is aimed at solving information security issues. The object of study: printed text and its characteristics. The subject of study: characteristics of text that describe the author's style, methods, and machine learning algorithms designed for processing both natural and artificially-generated texts. The research methods: set theory methods, mathematical statistics, computational experiments, and methods of artificial intelligence Scientific novelty: for the first time, a comprehensive methodology for identification of a text’s author and a model for text creation by an author in a cyber environment have been proposed. The proposed methodology considers features of both natural and artificially-generated texts. An introduced model takes into account semantic features and informative characteristics of the text at different levels of hierarchical analysis, specifics of the environment, author attributes, and the nature of activities involved in creating the text. Results obtained: a methodology has been proposed for identifying the author of a natural language text and program source codes to address information security challenges. The methodology includes a set of methods, models and algorithms that aggregate existing research experience. The methodology is universal for solving information security issues related to text classification.
Keywords: text mining, semantics, machine learning, source code, attribution.

1. Uslu U., Durmaz Ö., Alptekin G. I. Evaluation of Deep Learning Models for Continuous Authentication Using Behavioral Biometrics // Proceedings of 27th International Conference on Knowledge Based and Intelligent Information and Engineering Sytems (KES 2023), Procedia Computer Science. – 2023. – Vol. 225. – P. 1272–1281.
2. Bano H, Akbar W., Aslam N., Bilal M. Identification and Classification of Extremist by Topic Modeling Sentiment Analysis // VFAST Transactions on Software Engineering. – 2023. – Vol. 11. – P. 235–248.
3. Аванесян Н. Л., Соловьев Ф. Н., Тихомирова Е. А., Чеповский А. М. Выявление значимых признаков противоправных текстов // Вопросы кибербезопасности. – 2020. – № 4(38). – С. 76–84.
4. Васильев В. И., Вульфин А. М., Кучкарова Н. В. Тематическое моделирование и суммаризация текстов в области кибербезопасности // Вопросы кибербезопасности. – 2023. – № 2(54). – С. 1–22
5. Araque O., Iglesias C. A. An Approach for Radicalization Detection Based on Emotion Signals and Semantic Similarity // IEEE Access. – 2020. – Vol. 8. – P. 17877–17891.
6. Asad M., Shafiq Z., Srinivasan P. A Girl Has A Name: Detecting Authorship Obfuscation // Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics. – 2020. – P. 2235–2245.
7. Kovalev A. K., Kuznetsova Yu. M. Possibilities of automatic text analysis in the task of determining the psychological characteristics of the author // Experimental Psychology (Russia). – 2020. – Vol. 13, no. 1. – P. 149–158.
8. Москин Н. Д. Теоретико-графовые модели, методы и программные средства интеллектуального анализа текстовой информации
на примере фольклорных и литературных произведений: дис. д-р. техн. наук: 05.13.18. – Петрозаводский. гос. университет,
Петрозаводск, 2022. – 346 с.
9. Рогов А. А. Проблема атрибуции в журналах «Время», «Эпоха» и еженедельнике «Гражданин» / А. А. Рогов, Р. В. Абрамов,
Д. Д. Бучнева, О. В. Захарова, К. А. Кулаков, А. А. Лебедев и др. // Издательство «Острова». – 2021. – 391 с.
10. Огорелков И. В. Исследование лингвистических характеристик текста с целью определения пола автора на примере анализа письменных русскоязычных текстов политического дискурса: дис. канд. техн. наук: 10.02.01. – ФГБОУ ВО «Государственный институт русского языка им. А.С. Пушкина», Москва, 2021. – 457 с.
11. Огорелков И. В. Исследование лингвистических характеристик письменного текста политического дискурса с целью определения пола автора // Язык. Право. Общество: сб. ст. V Междунар. науч.-практ. конф. (г. Пенза, 22–25 мая 2018 г.) / под общ. ред. О. В. Барабаш; редколлегия: М. Б. Ворошилова, Т. В. Дубровская, А. К. Дятлова, Н. А. Павлова. – Пенза: Изд-во ПГУ, 2018. – 484 с. ISBN 978-5-907018-83-9. – 2018. – С. 88–93.
12. Сбоев А. Г. Нейросетевое моделирование и машинное обучение на основе экспериментальных и наблюдательных данных:
дис. д-р. техн. наук: 05.13.18. – Национальный исследовательский центр «Курчатовский институт», Москва, 2021. – 389 с.
13. Sboev A. Neural Network Model to Include Textual Dependency Tree Structure in Gender Classification of Russian Text Author / A. Sboev, A. Selivanov, R. Rybka, I. Moloshnikov, D. Bogachev // Advanced Technologies in Robotics and Intelligent Systems. – Springer, Cham, 2020. – P. 405–412.
14. Давыдова Ю. В. Методы текстового поиска и обработки информации в социальных сетях при управлении деятельностью
правоохранительных органов: дис. канд. техн. наук, 05.13.10. – ФГБОУ ВО «Орловский государственный университет имени
И. С. Тургенева», Белгород, 2021. – 146 с.
15. Андреев И. А. Исследование методов и алгоритмов обработки текстовой информации социальных сетей в задачах формирования социального портрета пользователя: дис. канд. техн. наук, 05.13.01. – Ульяновский государственный технический университет, Ульяновск, 2022. – 166 с.
16. Куртукова А. В., Романов А. С., Федотова А. М., Шелупанов А. А. Применение методов машинного обучения и отбора признаков на основе генетического алгоритма в решении задачи определения автора русскоязычного текста для кибербезопасности / А. В. Куртукова [и др.] // Доклады ТУСУР. – 2022. – Т. 25, № 1. – С. 79–85.
17. Романов А. С., Куртукова А. В., Шелупанов А. А., Федотова А. М. Идентификация автора исходного кода программы на
основе неоднородных данных для решения задач кибербезопасности / А. В. Куртукова, А. А. Шелупанов, А. М. Федотова //
Моделирование, оптимизация и информационные технологии. – 2022. – №10(3) [Электронный ресурс]. – URL: https://moitvivt.
ru/ru/journal/pdf?id=1227 DOI: 10.26102/2310-6018/2022.38.3.016.

The purpose of the article: to develop a method for detecting transactions made by customers exposed to fraud using social engineering methods based on the analysis of video data of a person using neural network methods of emotion recognition. Research method: analysis of modern neural network models and approaches used to solve the problem of emotion recognition; analysis of neural network architectures that process a video image or sequence of frames; development and software implementation of a method for detecting suspicious transactions using artificial neural networks based on video data of a person's face; experimental research and evaluation of the developed method. The result obtained: a method for detecting suspicious transactions based on neural network methods for recognizing the facial emotions of bank customers exposed to intruders has been developed. A combined neural network structure is implemented using an architecture suitable for processing graphical information and information presented in a time sequence to solve the problem of emotion recognition. A software prototype has been created that allows you to assess the emotional state of an observed person from video data of a person and is able to determine whether a person is in a negative emotional state. The results of the developed method were analyzed. Recommendations are given on the prospects of its application and further research on this topic. Scientific novelty: a new method for detecting suspicious transactions is proposed, based on solving the problem of recognizing emotions from video using a combination of CNN and LSTM architectures of neural networks.
Keywords:  long-term short-term memory, machine learning, emotion recognition, recurrent neural networks,
convolutional neural networks, CNN, LSTM.

1. Ahmad F. M. Mansor, Ahmad A. Zainuddin, Zulkeflee Khalidin. Patient Monitoring System using Computer Vision for Emotional Recognition and Vital Signs Detection. // ResearchGate: портал. – 2020. – URL: https://www.researchgate.net/publication/344399775_Patient_
Monitoring_System_using_Computer_Vision_for_Emotional_Recognition_and_Vital_Signs_Detection (дата обращения: 02.12.2023).
2. Mei Wang, Ziyang Huang, Yuancheng Li, Lihong Dong, Hongguang Pan. Maximum weight multi-modal information fusion algorithm of electroencephalographs and face images for emotion recognition // Computers & Electrical Engineering. – 2021. – Vol. 94. – DOI: 10.1016/j.compeleceng.2021.107319. – ISSN 0045-7906.
3. Cuiting Xu, Chunchuan Yan, Mingzhe Jiang, Fayadh Alenezi, Adi Alhudhaif, Norah Alnaim, Kemal Polat, Wanqing Wu. A novel facial emotion recognition method for stress inference of facial nerve paralysis patients // Expert Systems with Applications. – 2022. – Vol. 197. – DOI: 10.1016/j.eswa.2022.116705. – ISSN 0957-4174.
4. Shichuan Du, Aleix M. Martinez. Compound facial expressions of emotion: from basic research to clinical applications // Dialogues in Clinical Neuroscience. – 2015. – № 17:4. – Pages 443–455. – DOI: 10.31887/DCNS.2015.17.4/sdu.
5. Zhongshan Chen, Xinning Feng, Shengwei Zhang. Emotion detection and face recogni-tion of drivers in autonomous vehicles in IoT platform // Image and Vision Computing. – 2022. – Vol. 128. – DOI: 10.1016/j.imavis.2022.104569. – ISSN 0262-8856.
6. Zepf Sebastian, Hernandez Javier, Schmitt Alexander, Minker Wolfgang, Picard Rosalind. Driver Emotion Recognition for Intelligent Vehicles: A Survey // ACM Com-puting Surveys. – 2020. – DOI: 10.1145/3388790.
7. Lian H, Lu C, Li S, Zhao Y, Tang C, Zong Y. A Survey of Deep Learning-Based Mul-timodal Emotion Recognition: Speech, Text, and Face // Entropy (Basel). – 2023. – № 25(10):1440. – DOI: 10.3390/e25101440.
8. Prameela Naga, Swamy Das Marri, Raiza Borreo. Facial emotion recognition methods, datasets and technologies: A literature survey // Materials Today: Proceedings. – 2023. – Vol. 80. – Pages 2824–2828. – DOI: 10.1016/j.matpr.2021.07.046.
9. Chahak Gautam, K. R Seeja. Facial emotion recognition using Handcrafted features and CNN // Procedia Computer Science. – 2023. – Vol. 218. – Pages 1295–1303. – DOI: 10.1016/j.procs.2023.01.108.
10. Zia Ullah, Lin Qi, Asif Hasan, Muhammad Asim. Improved Deep CNN-based Two Stream Super Resolution and Hybrid Deep Modelbased Facial Emotion Recognition // Engineering Applications of Artificial Intelligence. – 2022. – Vol. 116. – DOI: 10.1016/j.engappai.2022.105486.
11. Elham S. Salama, Reda A. El-Khoribi, Mahmoud E. Shoman, Mohamed A. Wahby Shalaby. A 3D-convolutional neural network framework with ensemble learning tech-niques for multi-modal emotion recognition // Egyptian Informatics Journal. – 2021. – Vol. 22. – Issue 2. – Pages 167–176. – DOI: 10.1016/j.eij.2020.07.005.
12. Radha Priyadharsini G, Krishnaveni K. A novel framework using binary attention mechanism based deep convolution neural network for face emotion recognition // Measurement: Sensors. – 2023. – Vol. 30. – DOI: 10.1016/j.measen.2023.100881.
13. Anjali R, J. Babitha, Rithika W, Ms.Reeja S.L. Stress Detection Based on Emotion Recognition Using Deep Learning // National Conference on Smart Systems and Tech-nologies. – 2021. – Vol. 8. – Issue 7. – Pages 109–114.
14. Orhan Atila, Abdulkadir Şengür. Attention guided 3D CNN-LSTM model for accu-rate speech based emotion recognition // Applied Acoustics. – 2021. – Vol. 182. – DOI: 10.1016/j.apacoust.2021.108260.
15. Wafa Mellouk, Wahida Handouzi. CNN-LSTM for automatic emotion recognition using contactless photoplythesmographic signals // Biomedical Signal Processing and Control. – 2023. – Vol. 85. – DOI: 10.1016/j.bspc.2023.104907.
16. El Mehdi Saoudi, Jaafar Jaafari, Said Jai Andaloussi. Advancing human action recog-nition: A hybrid approach using attention-based LSTM
and 3D CNN // Scientific Afri-can. – 2023. – Vol. 21. – DOI: 10.1016/j.sciaf.2023.e01796.
17. Emanuel Di Nardo, Vincenzo Santopietro, Alfredo Petrosino. Emotion recognition at the edge with AI specific low power architectures // Microprocessors and Microsys-tems. – 2021. – Vol. 85. – DOI: 10.1016/j.micpro.2021.104299.
18. Yi Chen, Jun Bin, Chao Kang. Application of machine vision and convolutional neural networks in discriminating tobacco leaf maturity on mobile devices // Smart Agricultur-al Technology. – 2023. – Vol. 5. – DOI: 10.1016/j.atech.2023.100322.
19. Deyuan Qu, Sudip Dhakal, Dominic Carrillo. Facial Emotion Recognition using CNN in PyTorch. – URL: https://arxiv.org/pdf/2312.10818.pdf (дата обращения: 14.12.2023).
20. Glen Berman. Machine Learning practices and infrastructures. – URL: https://arxiv.org/pdf/2307.06518.pdf (дата обращения: 14.12.2023).
21. Ramesh Naidu P, Pruthvi Sagar S, Praveen K, Kiran K, Khalandar K. Stress Recogni-tion Using Facial Landmarks and Cnn (Alexnet) // Journal of Physics: Conference Series. – 2021. – 2089(1):012039 – DOI: 10.1088/1742-6596/2089/1/012039.
22. Xingxun Jiang, Yuan Zong, Wenming Zheng, Chuangao Tang, Wanchuang Xia, Cheng Lu, Jiateng Liu. DFEW: A Large-Scale Database for Recognizing Dynamic Fa-cial Expressions in the Wild // Proceedings of the 28th ACM International Conference on Multimedia. – 2020. – Pages 2881–2889. – DOI: 10.48550/arXiv.2008.05924.
23. Andrea Scarantino. Core Affect and Natural Affective Kinds // Philosophy of Science. – 2009. – Vol. 76. – Issue 5. – Pages 940–957. – DOI: 10.1086/605816

Purpose of the work: definition of common techniques, tactics and procedures for various methods of cryptanalysis of homomorphic ciphers based on the problem of factorization of numbers, and development of a system architecture independent of the applied cryptanalysis method to simplify this process by providing a convenient environment and tools. Research methods: analysis of possible implementations of architectural features in the creation of cryptanalysis systems for homomorphic ciphers based on the problem of number factorization. The object of research: homomorphic ciphers based on the problem of number factorization, cryptosystem MORE (Matrix Operation for Randomization or Encryption), cryptanalysis of homomorphic ciphers based on the problem of number factorization, features of the architecture of systems for cryptanalysis of homomorphic ciphers based on the problem of number factorization in various types of attacks. Research results: the architecture of a cryptanalysis system has been developed to assess the cryptographic strength of the ciphers in question, based on the task of factorizing numbers by conducting a comprehensive vulnerability analysis for various attacks. Using the example of an attack with a known plaintext on the MORE cryptosystem based on the number factorization problem, general architectural features and features peculiar to specific ciphers based on the number factorization problem and specific types of attacks are determined. Practical significance: the implementation of a cryptanalysis system based on the proposed architecture will allow researchers and cryptanalysts to study in more detail potential vulnerabilities in homomorphic cryptosystems based on the problem of number factorization, which will allow developing more effective measures to strengthen the durability of such ciphers.
Keywords:  Information security; confidential information; homomorphic encryption; cryptosystem MORE;
cryptanalysis; architecture of the cryptanalysis system.

1. Минаков С. С. Основные криптографические механизмы защиты данных, передаваемых в облачные сервисы и сети хранения данных // Вопросы кибербезопасности. – 2020. – № 3(37). – С. 66–75. DOI: 10.21681/2311-3456-2020-03-66-75
2. Гаража А. А., Герасимов И. Ю., Николаев М. В., Чижов И. В. Об использовании библиотек полностью гомоморфного шифрования // International Journal of Open Information Technologies. – 2021. – Т. 9, № 3. – С. 11–22.
3. Шачина В. А. Гомоморфная криптография в базах данных // Прикладная математика и информатика: современные исследования в области естественных и технических наук: Материалы V Международной научно-практической конференции (школы-семинара)
молодых ученых, Тольятти, 22–24 апреля 2019 года. – 2019. – С. 468–473.
4. Hariss K., Noura H., Samhat A. E. An efficient fully homomorphic symmetric encryption algorithm // Multimedia Tools and Applications. – 2020. – Т. 79. – №. 17. – С. 12139-12164. DOI:10.1007/s11042-019-08511-2
5. Иванов А. И., Сулавко А. Е. Проект третьего национального стандарта России по быстрому автоматическому обучению больших сетей корреляционных нейронов на малых обучающих выборках биометрических данных // Вопросы кибербезопасности. – 2021. – № 3 (43). – С. 84–93. DOI: 10.21681/2311-3456-2021-3-84-93
6. Sana M. U. et al. Enhanced security in cloud computing using neural network and encryption // IEEE Access. – 2021. – Т. 9. – С. 145785–145799. DOI:10.1109/ACCESS.2021.3122938
7. Тришин А. Е. Атака Винера и слабые ключи криптосистемы RSA // Дискретная математика. – 2023. – Т. 35. – №. 3. – С. 71–80. DOI: 10.4213/dm1773
8. Трепачева А. В. О стойкости гомоморфной криптосистемы Доминго-Феррера против атаки только по шифртекстам // Прикладная дискретная математика. Приложение. – 2023. – № 16. – С. 98–102. DOI: 10.17223/2226308X/16/25
9. Гантмахер Ф. Теория матриц. – Litres, 2022. 576 с.
10. Горохов Н. Б., Преображенский Ю. П. Об особенностях криптографических систем защиты информации // Молодежь и XXI век-2022. – 2022. – С. 43–46.
11. Vaudenay D. V. S. Cryptanalysis of enhanced more //Tatra Mt. Math. Publ. – 2019. – Т. 73. – С. 163-178. DOI: 10.2478/tmmp-2019-0012
12. Винберг Э. Курс алгебры. – Litres, 2022. 592 с.
13. Yuan Y., Mo Y. L. Security for cyber-physical systems: Secure control against known-plaintext attack // Science China Technological Sciences. – 2020. – Т. 63. – №. 9. – С. 1637–1646. DOI: 10.1007/s11431-020-1621-y
14. Bahar A. Y. et al. Survey on Features and Comparisons of Programming Languages (PYTHON, JAVA, AND C#) // 2022 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS). – IEEE, 2022. – С. 154-163. DOI: 10.1109/ICETSIS55481.2022.9888839
15. Нагибин В. А. Проектирование и реализация системы подключаемых модулей в приложениях на языке C# // Путь в науку: прикладная математика, информатика и информационные технологии. – 2023. – С. 27–29.
16. Jeong J., Zeng J., Jung C. Capri: Compiler and architecture support for whole-system persistence // Proceedings of the 31st International Symposium on High-Performance Parallel and Distributed Computing. – 2022. – С. 71-83. DOI: 10.1145/3502181.3531474
17. Волушкова В. Л. Многоуровневое логгирование работы процессов и задач // ИТНОУ: информационные технологии в науке,
образовании и управлении. – 2021. – №. 1 (17). – С. 60–64. DOI: 10.47501/ITNOU.2021.1.060-064
18. Киптенко А. В., Бахарева Н. Ф. Отладка программного обеспечения с помощью лог файлов //Актуальные проблемы информатики, радиотехники и связи. – 2023. – С. 157–158.
19. Jánki Z. R., Bilicki V. Rule-Based Architectural Design Pattern Recognition with GPT Models // Electronics. – 2023. – Т. 12. – №. 15. – С. 3364. DOI: 10.3390/electronics12153364
20. Pasztaleniec M., Skublewska-Paszkowska M. Comparative analysis of Windows Presentation Foundation and Windows Forms // Journal of Computer Sciences Institute. – 2020. – Т. 14. – С. 26-30. DOI: 10.35784/jcsi.1571