<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">vdgtu</journal-id><journal-title-group><journal-title xml:lang="ru">Вестник Дагестанского государственного технического университета. Технические науки</journal-title><trans-title-group xml:lang="en"><trans-title>Herald of Dagestan State Technical University. Technical Sciences</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2073-6185</issn><issn pub-type="epub">2542-095X</issn><publisher><publisher-name>Daghestan State Technical University</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.21822/2073-6185-2025-52-2-81-89</article-id><article-id custom-type="elpub" pub-id-type="custom">vdgtu-1773</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ И ТЕЛЕКОММУНИКАЦИИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>INFORMATION TECHNOLOGY AND TELECOMMUNICATIONS</subject></subj-group></article-categories><title-group><article-title>Гибридный метод моделирования систем искусственного интеллекта для выявления кибератак</article-title><trans-title-group xml:lang="en"><trans-title>A hybrid method for modeling artificial intelligence systems to detect cyberattacks</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0005-8562-9389</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Дубровина</surname><given-names>А. И.</given-names></name><name name-style="western" xml:lang="en"><surname>Dubrovina</surname><given-names>A. I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Ангелина Игоревна Дубровина, доцент</p><p>344002, г. Ростов-на-Дону, пл. Гагарина, 1</p></bio><bio xml:lang="en"><p>Angelina I. Dubrovina, Assoc. Prof.</p><p>1 Gagarina Square, Rostov-on-Don 344002</p></bio><email xlink:type="simple">ministrelia69@yandex.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Донской государственный технический университет</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Don State Technical University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>10</day><month>08</month><year>2025</year></pub-date><volume>52</volume><issue>2</issue><fpage>81</fpage><lpage>89</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Дубровина А.И., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Дубровина А.И.</copyright-holder><copyright-holder xml:lang="en">Dubrovina A.I.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://vestnik.dgtu.ru/jour/article/view/1773">https://vestnik.dgtu.ru/jour/article/view/1773</self-uri><abstract><p>Цель. Целью исследования является разработка адаптивной системы защиты критической инфраструктуры жизнеобеспечения на основе гибридных ИИ-методов, объединяющих машинное обучение (МО) и обучения с подкреплением. Метод. Используется гибридный метод моделирования систем искусственного интеллекта для выявления кибератак. Основой метода является комбинирование обучения с подкреплением и анализа аномалий, что позволяет системе автоматически адаптироваться к новым угрозам в процессе эксплуатации. Результат. Предложено внедрение систем искусственного интеллекта на этапах мониторинга, анализ полученных данных и оперативное реагирование по ликвидации угрозы. Система включает разработку гибридных моделей для анализа данных, которая объединяет информацию из внешних источников и журналов событий. Применение системы позволит повысить устойчивость инфраструктуры, снижая уязвимость к угрозам, обеспечивая бесперебойное функционирование в условиях информационной угрозы. Вывод. Рассмотрены новые подходы к использованию систем искусственного интеллекта для повышения эффективности защиты критической инфраструктуры объектов. Предложены модели искусственного интеллекта, основанные на машинном обучении, позволяющие обнаруживать за короткое время не только старые угрозы, но и нетипичные сценарии информационных взломов. Алгоритмы прогнозирования применяются для анализа и последующего исследования аномального поведения вредоносной системы, в то время, как глубокое обучение обеспечивает точное заключение по классификации угроз.</p></abstract><trans-abstract xml:lang="en"><p>Objective. The aim of the research is to develop an adaptive system for protecting critical life support infrastructure based on hybrid AI methods that combine machine learning (ML) and reinforcement learning. Method. A hybrid method of modeling artificial intelligence systems to detect cyber attacks is used. The basis of the method is a combination of reinforcement learning and anomaly analysis, which allows the system to automatically adapt to new threats. Result. It is proposed to implement artificial intelligence systems at the stages of monitoring, analysis of the received data and prompt response to eliminate the threat. The system includes the development of hybrid models for data analysis, which combines information from external sources and event logs. The use of the system will increase the stability of the infrastructure, reduce vulnerability to threats, and ensure uninterrupted operation in the conditions of an information threat. Conclusion. New approaches to the use of artificial intelligence systems are considered. Artificial intelligence models based on machine learning are proposed, allowing for the detection of not only old threats but also atypical scenarios of information hacks in a short time. Predictive algorithms are used to analyze the abnormal behavior of the malicious system, and deep learning provides accurate conclusions about threat classification.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>системный анализ</kwd><kwd>ИИ</kwd><kwd>машинное обучение</kwd><kwd>обучение с подкреплением</kwd></kwd-group><kwd-group xml:lang="en"><kwd>system analysis</kwd><kwd>AI</kwd><kwd>machine learning</kwd><kwd>reinforcement learning</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Шелухин В.В., Зегжда Д.П. Интеллектуальные технологии информационной безопасности. М.: МГТУ им. Н.Э. Баумана, 2021. 320 с.</mixed-citation><mixed-citation xml:lang="en">Shelukhin V.V., Zeghda D.P. Intelligent Technologies for Information Security. Moscow: MSTU Publishing House, 2021. 320 p. (In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Лю Ю. Обучение с подкреплением на PyTorch: Сборник рецептов. СПб.: Питер, 2020. 400 с.</mixed-citation><mixed-citation xml:lang="en">Liu Y. Reinforcement Learning with PyTorch: A Cookbook. St. Petersburg: Peter, 2020. 400 p. (In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Xu S., Qian Y., Hu R.Q. Cybersecurity in Intelligent Networking Systems. New Jersey: Wiley-IEEE Press, 2019. 368 p.</mixed-citation><mixed-citation xml:lang="en">Xu S., et al. Cybersecurity in Intelligent Networking Systems. New Jersey: Wiley-IEEE Press, 2019. 368 p.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Goodfellow I., et al. Deep learning. MIT press, 2016. 800 p.</mixed-citation><mixed-citation xml:lang="en">Goodfellow I., et al. Deep Learning. MIT Press, 2016. 800 p.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Alavizadeh H., et al. Deep Reinforcement Learning for Cybersecurity: A Comprehensive Review. IEEE Access, 2023, vol. 11, p. 12392-12416.</mixed-citation><mixed-citation xml:lang="en">Alavizadeh H., et al. Deep Reinforcement Learning for Cybersecurity: A Comprehensive Review. IEEE Access, 2023;11:12392-12416.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Sutton R.S., Barto A.G. Reinforcement Learning: An Introduction. 2nd ed. Cambridge: MIT Press, 2018. 552 p.</mixed-citation><mixed-citation xml:lang="en">Sutton R.S., Barto A.G. Reinforcement Learning: An Introduction. 2nd ed. Cambridge: MIT Press, 2018. 552 p.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Kaspersky K., et al. Advanced Persistent Threats: Detection, Analysis, and Protection. Berlin: Springer, 2020. 278 p.</mixed-citation><mixed-citation xml:lang="en">Kaspersky K., et al. Advanced Persistent Threats: Detection, Analysis, and Protection. Berlin: Springer, 2020. 278 p.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Гаврилов А.В., Петренко С.А. Машинное обучение в задачах кибербезопасности. М.: ДМК Пресс, 2022. 192 с.</mixed-citation><mixed-citation xml:lang="en">Gavrilov A.V., Petrenko S.A. Machine Learning in Cybersecurity Tasks. Moscow:DMK Press, 2022. 192p. (In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Silver D., et al. Mastering the game of Go with deep neural networks and tree search. Nature, 2016, vol. 529, p. 484-489. DOI: 10.1038/nature16961</mixed-citation><mixed-citation xml:lang="en">Silver D., et al. Mastering the game of Go with deep neural networks and tree search. Nature, 2016; 529: 484-489.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Липаев В.В. Защита критической инфраструктуры от кибератак. СПб.: Лань, 2021. 245 с.</mixed-citation><mixed-citation xml:lang="en">Lipaev V.V. Protection of Critical Infrastructure from Cyber Attacks. St.Petersburg: Lan, 2021;245(In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Mnih V., et al. Human-level control through deep reinforcement learning. Nature, 2015; 518:529-533.</mixed-citation><mixed-citation xml:lang="en">Mnih V., et al. Human-level control through deep reinforcement learning. Nature, 2015; 518:529-533.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Осипов Д.С. Нейронные сети для анализа сетевого трафика. М.: Инфра-Инженерия, 2023. 168 с.</mixed-citation><mixed-citation xml:lang="en">Osipov D.S. Neural Networks for Network Traffic Analysis. Moscow: Infra-Engineering, 2023. 168 p. (In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Carlini N., Wagner D. Adversarial Examples: Attacks and Defenses. arXiv:1802.00420, 2019.</mixed-citation><mixed-citation xml:lang="en">Carlini N., Wagner D. Adversarial Examples: Attacks and Defenses. arXiv:1802.00420, 2019.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Миронов А.А., Соколова Е.В. Глубокое обучение в защите данных. Новосибирск: НГУ, 2022. 210 с.</mixed-citation><mixed-citation xml:lang="en">Mironov A.A., Sokolova E.V. Deep Learning in Data Protection. Novosibirsk: NSU, 2022. 210 p.(In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">LeCun Y., Bengio Y., Hinton G. Deep learning. Nature, 2015, vol. 521, p. 436-444.</mixed-citation><mixed-citation xml:lang="en">LeCun Y., Bengio Y., Hinton G. Deep learning. Nature, 2015;521:436-444.</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Шнайер Б. Прикладная криптография. М.: Триумф, 2020. 816 с.</mixed-citation><mixed-citation xml:lang="en">Schneier B. Applied Cryptography. Moscow: Triumph, 2020. 816 p. (In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Papernot N., et al. Practical Black-Box Attacks Against Machine Learning. ACM CCS, 2017, p. 506-519.</mixed-citation><mixed-citation xml:lang="en">Papernot N., et al. Practical Black-Box Attacks Against Machine Learning. ACM CCS, 2017; 506-519.</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Tanenbaum A.S., Wetherall D. Computer Networks. 6th ed. New Jersey: Pearson, 2021. 960 p.</mixed-citation><mixed-citation xml:lang="en">Tanenbaum A.S., Wetherall D. Computer Networks. 6th ed. New Jersey: Pearson, 2021. 960 p.</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Крутов А.Н., Белов А.И. Искусственный интеллект в энергетике. М.: Энергоатомиздат, 2023. 304 с.</mixed-citation><mixed-citation xml:lang="en">Krutov A.N., Belov A.I. Artificial Intelligence in Energy. Moscow:Energoatomizdat, 2023.304 p.(In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Madry A., et al. Towards Deep Learning Models Resistant to Adversarial Attacks. ICLR, 2018.</mixed-citation><mixed-citation xml:lang="en">Madry A., et al. Towards Deep Learning Models Resistant to Adversarial Attacks. ICLR, 2018.</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
