30

Mazkur tadqiqot Internet narsalar (IoT) tizimlariga qaratilgan 
kiberhujumlarni aniqlash hamda bartaraf etish uchun yangi algoritm va 
modellarni ishlab chiqishga bag‘ishlangan. IoT qurilmalarining keng tarqalishi 
axborot xavfsizligiga jiddiy tahdid solmoqda, chunki ularning ko‘pchiligi resurs 
jihatdan cheklangan va zamonaviy xavfsizlik mexanizmlariga ega emas. Shu 
sababli maqolada IoT tizimlarida yuzaga keladigan asosiy xavf-xatarlar, hujum 
turlari (masalan, DoS, spoofing, sniffing) va ularni aniqlashda qo‘llanadigan 
usullar (aniqlovchi modellar, mashinaviy o‘rganish algoritmlari) yoritilgan. 
Xususan, an’anaviy statistik yondashuvlar bilan bir qatorda, sun’iy intellekt va 
chuqur o‘rganishga asoslangan algoritmlarning afzalliklari ko‘rsatib berilgan. 
Maqolada anomaliyalarni aniqlash, tarmoq trafigi tahlili va xavfni aniq vaqtda 
identifikatsiyalash uchun gibrid yondashuv taklif etilgan. Tadqiqot doirasida 
IoT qurilmalaridan 12 oy davomida yig‘ilgan 100 GB hajmdagi ma’lumotlar 
to‘plamidan foydalanildi. Taklif etilgan gibrid model sodda mashinali o‘rganish 
usullariga nisbatan 94,7 % aniqlik ko‘rsatkichi bilan 27 % yaxshilanishni ko‘rsatdi. 
Bundan tashqari, ushbu model false-positiv ko‘rsatkichlarni 35 %gacha kamaytirdi 
va real vaqt rejimida ishlov berish tezligini 2,3 barobar oshirdi. Tadqiqot natijalari 
IoT xavfsizligi sohasida muhim yutuq hisoblanadi va sanoat muhitida amaliy 
qo‘llash uchun yangi usullar taklif etadi.

  • Internet ҳавола
  • DOI
  • UzSCI тизимида яратилган сана 12-06-2025
  • Ўқишлар сони 30
  • Нашр санаси 02-06-2025
  • Мақола тилиO'zbek
  • Саҳифалар сони17-28
Ўзбек

Mazkur tadqiqot Internet narsalar (IoT) tizimlariga qaratilgan 
kiberhujumlarni aniqlash hamda bartaraf etish uchun yangi algoritm va 
modellarni ishlab chiqishga bag‘ishlangan. IoT qurilmalarining keng tarqalishi 
axborot xavfsizligiga jiddiy tahdid solmoqda, chunki ularning ko‘pchiligi resurs 
jihatdan cheklangan va zamonaviy xavfsizlik mexanizmlariga ega emas. Shu 
sababli maqolada IoT tizimlarida yuzaga keladigan asosiy xavf-xatarlar, hujum 
turlari (masalan, DoS, spoofing, sniffing) va ularni aniqlashda qo‘llanadigan 
usullar (aniqlovchi modellar, mashinaviy o‘rganish algoritmlari) yoritilgan. 
Xususan, an’anaviy statistik yondashuvlar bilan bir qatorda, sun’iy intellekt va 
chuqur o‘rganishga asoslangan algoritmlarning afzalliklari ko‘rsatib berilgan. 
Maqolada anomaliyalarni aniqlash, tarmoq trafigi tahlili va xavfni aniq vaqtda 
identifikatsiyalash uchun gibrid yondashuv taklif etilgan. Tadqiqot doirasida 
IoT qurilmalaridan 12 oy davomida yig‘ilgan 100 GB hajmdagi ma’lumotlar 
to‘plamidan foydalanildi. Taklif etilgan gibrid model sodda mashinali o‘rganish 
usullariga nisbatan 94,7 % aniqlik ko‘rsatkichi bilan 27 % yaxshilanishni ko‘rsatdi. 
Bundan tashqari, ushbu model false-positiv ko‘rsatkichlarni 35 %gacha kamaytirdi 
va real vaqt rejimida ishlov berish tezligini 2,3 barobar oshirdi. Tadqiqot natijalari 
IoT xavfsizligi sohasida muhim yutuq hisoblanadi va sanoat muhitida amaliy 
qo‘llash uchun yangi usullar taklif etadi.

Русский

Данное исследование посвящено разработке новых алгоритмов 
и моделей для выявления и предотвращения кибератак, направленных на 
системы интернета вещей (IoT). Широкое распространение IoT-устройств 
представляет серьёзную угрозу информационной безопасности, поскольку 
большинство таких устройств имеют ограниченные ресурсы и не оснащены 
современными механизмами защиты. В статье рассмотрены основные 
риски и угрозы, возникающие в IoT-среде, а также виды атак (например, 
DoS, spoofing, sniffing) и методы их обнаружения (детектирующие модели, 
алгоритмы машинного обучения). Особое внимание уделено преимуществам 
алгоритмов, основанных на искусственном интеллекте и глубоком 
обучении, по сравнению с традиционными статистическими подходами. 
В работе предложен гибридный подход для выявления аномалий, анализа 
сетевого трафика и оперативной идентификации угроз в реальном времени. 
В рамках исследования использовался датасет объёмом 100 ГБ, собранный 
в течение 12 месяцев с IoT-устройств. Предложенная гибридная модель 
показала улучшение точности на 27 % по сравнению с простыми методами 
машинного обучения, достигнув показателя точности 94,7 %. Кроме того, 
удалось снизить уровень ложноположительных срабатываний до 35 % и 
увеличить скорость обработки в реальном времени в 2,3 раза. Полученные 
результаты представляют собой значительное достижение в области IoT-безопасности и предлагают новые практические решения для применения в 
промышленной среде.

English

This study focuses on the development of new algorithms and models 
for detecting and mitigating cyberattacks targeting Internet of Things (IoT) 
systems. The widespread use of IoT devices poses a serious threat to information 
security, as most of these devices are resource-constrained and lack modern 
security mechanisms. The paper carefully looks at the main dangers and kinds 
of attacks in IoT systems (like DoS, spoofing, and sniffing), along with the 
methods used to detect them, which include detection models and machine 
learning algorithms. In particular, the advantages of artificial intelligence and 
deep learning-based algorithms over traditional statistical approaches are 
highlighted. We propose a hybrid approach for anomaly detection, network 
traffic analysis, and real-time threat identification. The research utilizes a 100 
GB dataset collected over 12 months from IoT devices. The proposed hybrid 
model demonstrated a 27% improvement in accuracy compared to basic machine 
learning methods, achieving an accuracy rate of 94.7%. Additionally, our model 
reduced false-positive rates by up to 35% and increased real-time processing 
speed by a factor of 2.3. The results of this research represent a major advance 
in IoT security and introduce novel methods suitable for practical application in 
industrial environments.

Муаллифнинг исми Лавозими Ташкилот номи
1 O'rinov .T. “Axborot texnologiyalari” kafedrasi mudiri, dotsent Zahiriddin Muhammad Bobur nomidagi Andijon davlat universiteti
Ҳавола номи
1 Anthi, E., Williams, L., Słowińska, M., Theodorakopoulos, G., & Burnap, P. (2018). A supervised intrusion detection system for smart home IoT devices. IEEE Internet of Things Journal, 6(5), 9042– 9053. https://doi.org/10.1109/JIOT.2019.2926365
2 Azmoodeh, A., Dehghantanha, A., Conti, M., & Choo, K.-K. R. (2018). Detecting crypto- ransomware in IoT networks based on energy consumption footprint. Journal of Ambient Intelligence and Humanized Computing, 9(4), 1141–1152. https://doi.org/10.1007/s12652-017-0558-5
3 Bertino, E., & Islam, N. (2017). Botnets and Internet of Things Security. Computer, 50(2), 76–79. https://doi.org/10.1109/MC.2017.62
4 European Union Agency for Cybersecurity (ENISA). (2020). ENISA Threat Landscape 2020 – Internet of Things. https://www.enisa.europa.eu/publications/enisa-threat-landscape-2020-internet- of-things
5 Falco, G., Eling, M., Jablanski, D., Weber, M., Miller, V., Gordon, L. A., Wang, S. S., Schmit, J., Thomas, R., Elvedi, M., Murakami, T., Lau, H., & Sharot, M. (2019). Cyber risk research impeded by disciplinary barriers. Science, 366(6469), 1066–1069. https://doi.org/10.1126/science.aaz4795
6 Garcia-Teodoro, P., Fernandez, M., Macia-Fernandez, G., & Tapiador, J. E. (2022). Ransomware: An interdisciplinary technical and legal approach. Security and Communication Networks, 2022, Article ID 2806605. https://doi.org/10.1155/2022/2806605
7 Hameed, S., Khan, F. I., & Hameed, B. (2019). Understanding security requirements and challenges in Internet of Things (IoT): A review. Journal of Computer Networks and Communications, 2019, 1–14. https://doi.org/10.1155/2019/9629381
8 Hasan, M., Islam, M. M., Zarif, M. I. I., & Hashem, M. M. A. (2019). Attack and anomaly detection in IoT sensors in IoT sites using machine learning approaches. Internet of Things, 7, 100059. https://doi. org/10.1016/j.iot.2019.100059
9 Hodo, E., Bellekens, X., Hamilton, A., Dubouilh, P.-L., Iorkyase, E., Tachtatzis, C., & Atkinson, R. (2016). Threat analysis of IoT networks using arti�icial neural network intrusion detection system. In 2016 International Symposium on Networks, Computers and Communications (ISNCC) (pp. 1–6). https://doi.org/10.1109/ISNCC.2016.7746067
10 Jan, S. U., Ahmed, S., Shakhshir, V., & Alahmadi, A. A. (2021). A comprehensive survey on machine learning-based big data analytics for IoT-enabled smart healthcare system. Mobile Networks and Applications, 26(1), 234–252. https://doi.org/10.1007/s11036-020-01700-6
11 Jung, W., Zhao, H., Sun, M., & Zhou, G. (2022). IoT botnet detection via power consumption modeling and deep learning. IEEE Transactions on Smart Grid, 13(1), 605–618. https://doi. org/10.1109/TSG.2021.3132578
12 Khan, M. A., & Salah, K. (2018). IoT security: Review, blockchain solutions, and open challenges. Future Generation Computer Systems, 82, 395–411. https://doi.org/10.1016/j.future.2017.11.022
13 Kim, J.-e., Park, T.-s., & Kim, K. J. (2022). The clinical effects of type 2 diabetes patient management using digital healthcare technology: A systematic review and meta-analysis. Healthcare, 10(3), 522. https://doi.org/10.3390/healthcare10030522
14 Li, X., Wen, Z., Cui, L., et al. (2023). Quantitatively mapping the research status and trends of vegetation responses to climate change with bibliometric analysis. Journal of Soils and Sediments, 23(8), 2963–2979. https://doi.org/10.1007/s11368-023-03583-y
15 Liu, X., Yang, T., & Yan, J. (2020). LSTM network based intrusion detection method for industrial control systems. Computers & Electrical Engineering, 84, 106619. https://doi.org/10.1016/j. compeleceng.2020.106619
16 Liu, Z., Lu, W., Yu, X., Rodriguez-Andina, J. J., & Gao, H. (2022). Approximation-Free Robust Synchronization Control for Dual-Linear-Motors-Driven System with Uncertainties and Disturbances. IEEE Transactions on Industrial Electronics, 69(10), 10500–10509. https://doi.org/10.1109/TIE.2022.3144567
17 Mao, Y., You, C., Zhang, J., Huang, K., & Letaief, K. B. (2017). A survey on mobile edge computing: The communication perspective. IEEE Communications Surveys & Tutorials, 19(4), 2322–2358. https:// doi.org/10.1109/COMST.2017.2745201
18 Mosenia, A., & Jha, N. K. (2023). A Comprehensive Study of Security of Internet-of-Things. IEEE Transactions on Emerging Topics in Computing. https://doi.org/10.1109/TETC.2023.3317675
19 Moustafa, N., Turnbull, B., & Choo, K.-K. R. (2019). An ensemble intrusion detection technique based on proposed statistical flow features for protecting network traffic of Internet of Things. IEEE Internet of Things Journal, 6(3), 4815–4830. https://doi.org/10.1109/JIOT.2018.2871719
20 Nguyen, T. N., Ngo, Q. D., Nguyen, H. T., & Giang, N. L. (2022). An advanced computing approach for IoT-botnet detection in industrial internet of things. IEEE Transactions on Industrial Informatics, 18(9), 6486–6494. https://doi.org/10.1109/TII.2022.3152814
21 Özkaynak, F., Çelik, M., & Dağ, A. (2020). A novel deep learning model for network anomaly detection and classification. IEEE Transactions on Network and Service Management, 17(4), 2159– 2170. https://doi.org/10.1109/TNSM.2020.3014929
22 Pajouh, H. H., Javidan, R., Khayami, R., Ali, D., & Choo, K.-K. R. (2019). A two-layer dimension reduction and two-tier classification model for anomaly-based intrusion detection in IoT backbone networks. IEEE Transactions on Emerging Topics in Computing, 7(2), 314–323. https://doi. org/10.1109/TETC.2016.2633228
23 Pamukov, M. E., Poulkov, V. K., & Shterev, V. A. (2018). Negative selection and neural network based algorithm for intrusion detection in IoT. In 2018 41st International Conference on Telecommunications and Signal Processing (TSP) (pp. 1–5). https://doi.org/10.1109/ TSP.2018.8441477
24 Raza, M. A., Aziz, S., Tuersun, A., Noreen, M., Iqbal, M. Z., & Iftikhar, D. (2023). Social media as a tool for professional development, advancement and presentation of pharmacist expanded roles. International Journal of Pharmacy and Chemistry, 9(2), 14–20. https://doi.org/10.11648/j.ijpc.20230902.11
25 Sicari, S., Rizzardi, A., Grieco, L. A., & Coen-Porisini, A. (2015). Security, privacy and trust in Internet of Things: The road ahead. Computer Networks, 76, 146–164. https://doi.org/10.1016/j. comnet.2014.11.008
26 Yang, K., Zhou, Y., Zomaya, A. Y., & Li, Q. (2023). Federated learning for IoT security: A survey. IEEE Internet of Things Journal, 10(2), 1217–1246. https://doi.org/10.1109/JIOT.2022.3186109
27 Yaseen, A., et al. (2024a). Baseline characteristics of SARS-CoV-2 vaccine non-responders in a large population-based sample. PLOS ONE, 19(5), e0303420. https://doi.org/10.1371/journal. pone.0303420
28 Yaseen, Q. M., Aldwairi, M., & Manasrah, A. (2024b). A Reputation-Based AODV Protocol for Blackhole and Malfunction Nodes Detection and Avoidance. Computers, Materials & Continua, 80(2), 1867–1888. https://doi.org/10.32604/cmc.2024.051179
29 Zhou, Z., Yu, X., Li, W., Luo, C., Ren, L., & Luo, J. (2020). Blockchain-empowered secure spectrum sharing for 5G heterogeneous networks. IEEE Network, 34(1), 24–31. https://doi.org/10.1109/ MNET.001.1900251
Кутилмоқда