USING A HYBRID CNN–LSTM ARCHITECTURE FOR DEEP LEARNING-DRIVEN ANOMALY DETECTION IN COMPUTER NETWORKS

Rustamov S. .


Annotatsiya

It's quite crucial to find weird things that will keep computer networks safe and running. Normal statistical and machine learning methods don't always perform well when you're working with traffic data that is both high-dimensional and sequential. This means that they might not be able to see patterns of abuse that are hard to spot and change over time. This study presents a hybrid deep learning architecture that combines Convolutional Neural Networks (CNN) with Long Short-Term Memory (LSTM) networks for the detection of anomalous activity in computer networks. The CNN part looks for connections between traffic patterns in space, and the LSTM part looks for connections between traffic patterns in time. On normal datasets, the suggested CNN-LSTM model works far better than regular machine learning and single deep learning models. It is more accurate, has a higher F1 score, and fewer false alarms. The results show that hybrid spatial-temporal learning is a good and flexible way to protect networks.


Adabiyotlar

  1. Khasanovich, R. S. (2021). METHODS OF ORGANIZING TRAINING WITH THE HELP OF AN INTELLIGENT TRAINING SYSTEM. Berlin Studies Transnational Journal of Science and Humanities, 1(1.5 Pedagogical sciences).
  2. RUSTAMOV, S. (2024). O ‘QITISHNING USLUBIY TIZIMINING MUVOFIQLASHTIRUVCHI MODELINI SHAKLLANTIRISH VAZIFALARI. «ACTA NUUz», 1(1.7), 176-178.
  3. Berdiev G.R., Norboev B.U., Normurodov B.B. USING AI TO MAKE A SOPHISTICATED DECISION-MAKING SYSTEM THAT CAN ADVISE YOU IN REAL TIME WHETHER TO STOP OR KEEP GOING AT PEDESTRIAN CROSSINGS // Universum: технические науки : электрон. Научн. Журн. 2026. 1(142). URL: https://7universum.com/ru/tech/archive/item/21672 (дата обращения: 10.01.2026).
  4. Норбоев Б.У., Нусратова Ш.Б. ADVANCED BIOMETRIC AUTHENTICATION SYSTEMS: AN IN-DEPTH STUDY OF ALGORITHMIC MODELS, SECURITY THREATS, AND MULTIMODAL EVALUATION FRAMEWORKS // Universum: технические науки : электрон. научн. журн. 2026. 1(142). URL: https://7universum.com/ru/tech/archive/item/21712 (дата обращения: 10.01.2026).
  5. Норбоев Б.У., Андокулов Т.Х. ADAPTIVE MULTIMODAL BIOMETRIC AUTHENTICATION SYSTEMS: A HUMAN-CENTERED ANALYSIS OF DESIGN, EVALUATION, AND SECURITY CHALLENGES // Universum: технические науки : электрон. научн. журн. 2026. 1(142). URL: https://7universum.com/ru/tech/archive/item/21701 (дата обращения: 10.01.2026).
  6. Pardayeva G.A. A PROJECT-BASED WAY TO USE OPEN BIOLOGICAL DATA IN BIOINFORMATICS EDUCATION // Universum: психология и образование : электрон. научн. журн. 2025. 1(139). URL: https://7universum.com/ru/psy/archive/item/21705 (дата обращения: 10.01.2026).
  7. Shoniyozova, Y. Q., Turdiyeva, M. A., & Norboyev, B. U. (2020). NETWORK ATTACK PREVENTION SYSTEMS. ИННОВАЦИОННЫЕ МЕХАНИЗМЫ И СТРАТЕГИЧЕСКИЕ ПРИОРИТЕТЫ НАУЧНО, 46.
  8. Rustamov, A. B. (2024). DEVELOPMENT OF SOFTWARE FOR DIGITAL INDUSTRIAL STRUCTURE TRANSFORMATION PROCESSES. Экономика и социум, (6-2 (121)), 593-597.
  9. Kadyrov, B. K. (2022). Perspectives of problems in the study of database science in the Credit-Module System and their solutions. International Journal of Formal Education, 2(1), 16-22.
  10. Ортиков, М. С. (2020). Расчет переходных процессов в соленоиде размагничивающего устройства рельсовых плетей при включении его на импульсное воздействие. Universum: технические науки, (10-3 (79)), 46-52.
  11. Meyliev A.R. MODELS FOR DEVELOPING STUDENTS’ COMPETENCE IN THE FIELD OF ARTIFICIAL INTELLIGENCE // Universum: психология и образование : электрон. научн. журн. 2025. 1(139). URL: https://7universum.com/ru/psy/archive/item/21720 (дата обращения: 10.01.2026).
  12. Kodirov B. THE IMPORTANCE OF A COMPETENCY-BASED APPROACH IN DATA ANALYSIS // Universum: психология и образование : электрон. научн. журн. 2025. 1(139). URL: https://7universum.com/ru/psy/archive/item/21724 (дата обращения: 10.01.2026).
  13. Ishqobilov, F. X. (2018). ELEKTRON DARSLIK YARATISHDA SERIF WEBPLUS X8 DASTURI IMKONIYATLARIDAN FOYDALANISH. Интернаука, (24-3), 50-52.
  14. Ишкобилов, Ф. Х. (2025). РОЛЬ ИСКУССТВЕННОГО ИНТЕЛЛЕКТА В ОБРАЗОВАНИИ. INNOVATIVE ACHIEVEMENTS IN SCIENCE 2024, 4(38), 238-241.
  15. Ишқобилов, Ф. Х. (2021). КОМПЬЮТЕР ИМИТАЦИОН МОДЕЛЛАРИ АСОСИДА ЎҚУВЧИЛАРНИНГ ЗООЛОГИЯ ФАНИ БЎЙИЧА БИЛИМЛАРИНИ ОШИРИШ МЕТОДИКАСИ. Современное образование (Узбекистан), (10 (107)), 57-63.
  16. Rakhmatillayevich, A. M. (2025). GLOVE: GLOBAL VECTORS FOR WORD REPRESENTATION. AMERICAN JOURNAL OF MULTIDISCIPLINARY BULLETIN, 3(5), 359-364.
  17. Raxmatillayevich, M. A. (2025). SUN'IY INTELLEKTGA ASOSLANGAN FARMATSEVTIKA SANOATI. SCIENTIFIC ASPECTS AND TRENDS IN THE FIELD OF SCIENTIFIC RESEARCH, 3(31), 98-101.
  18. Bekhzod, N., & Berdiev, G. (2023). Development of a System for Automating the Process of Lending to Individuals in Banks. American Journal of Public Diplomacy and International Studies (2993-2157), 12, 21.