Vol. 3 No. 7 (2026), Articles
Vol. 3 No. 7 (2026)

RESURS JIHATDAN CHEKLANGAN IOT QURILMALARI UCHUN YENGIL KIRISHNI ANIQLASH TIZIMLARI: RESURS BYUDJETIGA ASOSLANGAN QAROR QABUL QILISH MODELI

Articles
Published 2026-10-04
Maxamatjonov Ismoil Dilshod o‘g‘li
«Kiberxavfsizlik va kriminalistika» kafedrasi o‘qituvchisi, Muhammad al-Xorazmiy nomidagi Toshkent axborot texnologiyalari universiteti.
PDF

Keywords

Internet buyumlar xavfsizligi, yengil kirishni aniqlash tizimi, resurslari cheklangan qurilmalar, modelni siqish, edge-cloud arxitekturasi, qaror qabul qilish qoidasi.

Abstract

Internet buyumlar (IoT) qurilmalarining xotira, hisoblash quvvati va energiya iste’moli bo‘yicha qattiq cheklovlari ularda an’anaviy, resurs talab qiluvchi kirishni aniqlash tizimlarini (IDS) to‘g‘ridan-to‘g‘ri joylashtirishni amaliy jihatdan imkonsiz qiladi. Bu esa mazkur qurilmalarni ilg‘or doimiy tahdidlar, xizmat ko‘rsatishni rad etish (DoS/DDoS) hujumlari va ma’lumotlar sizib chiqishiga nisbatan zaif qoldiradi.

Ushbu maqolada resurs jihatdan cheklangan qurilmalar uchun yengil IDS (L-IDS) yondashuvlari tizimli adabiyotlar tahlili asosida ko‘rib chiqiladi. Shuningdek, qurilmaning resurs byudjeti hamda mahalliy tasniflash bilan bulutga topshirish o‘rtasidagi tanlovni tavsiflovchi rasmiy model taklif etiladi. Ko‘rib chiqilgan natijalarga ko‘ra:

  • CatBoost asosidagi tasniflagich ESP32 mikrokontrollerida 276 mikrosoniyalik kechikish bilan 99 foizga yaqin aniqlikka erishadi;
  • Bilim distillyatsiyasi chuqur model parametrlari sonini 70 foizga qisqartirib, STM32L4 platformasida 10 millisoniyadan kam xulosa chiqarish vaqtini ta’minlaydi;
  • Dinamik kvantlash esa model hajmini 4 MB dan 512 KB gacha siqib, aniqlikni taxminan 92 foiz darajasida saqlab qoladi;
  • Federativ edge-cloud arxitekturasi 95,6 foizlik aniqlikka erishishga, FPGA asosidagi Modbus yechimi esa o‘tkazuvchanlikni uch baravar oshirib, protsessor yukini 50 foizdan 15 foizgacha kamaytirishga imkon beradi.

Ushbu natijalar resurs byudjetini uchlik ko‘rinishida rasmiylashtirish va ishonch darajasiga asoslangan edge-cloud qaror qabul qilish qoidasini taqdim etish uchun asos bo‘lib xizmat qiladi.

PDF

References

[1] Mensah, C., Makhamatdjonov, I., Jin, H., & Yu, S. (2025). SoK: Lightweight intrusion detection and automated response for resource-constrained IoT embedded systems [Unpublished coursework report, COM6017: Security of Control and Embedded Systems]. University of Sheffield.

[2] Chiba, Z., Abghour, N., Moussaid, K., Lifandali, O., & Kinta, R. (2022). Review of recent intrusion detection systems and intrusion prevention systems in IoT networks. In 2022 International Conference on Software, Telecommunications and Computer Networks (SoftCOM) (pp. 1–6).

[3] Hasan, T., Hossain, A., Ansari, M. Q., & Syed, T. H. (2025). Enhanced intrusion detection in IIoT networks: A lightweight approach with autoencoder-based feature learning (arXiv:2501.15266). arXiv. https://doi.org/10.48550/arXiv.2501.15266

[4] Wang, Z., Chen, H., Yang, S., Luo, X., Li, D., & Wang, J. (2023). A lightweight intrusion detection method for IoT based on deep learning and dynamic quantization. PeerJ Computer Science, 9, e1569. https://doi.org/10.7717/peerj-cs.1569

[5] Belarbi, O., Spyridopoulos, T., Anthi, E., Mavromatis, I., Carnelli, P., & Khan, A. (2023). Federated deep learning for intrusion detection in IoT networks. In GLOBECOM 2023 – 2023 IEEE Global Communications Conference (pp. 237–242).

[6] Mofidi, F., Hounsinou, S., & Bloom, G. (2023). L-IDS: A lightweight hardware-assisted IDS for IoT systems to detect ransomware attacks. In Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementation (IoTDI ’23) (pp. 464–465). ACM. https://doi.org/10.1145/3576842.3589170

[7] Jouhari, M., & Guizani, M. (2024). Lightweight CNN-BiLSTM based intrusion detection systems for resource-constrained IoT devices. In 2024 International Wireless Communications and Mobile Computing (IWCMC) (pp. 1558–1563).

[8] Wang, C., Xu, D., Li, Z., & Niyato, D. (2024). Effective intrusion detection in highly imbalanced IoT networks with lightweight S2CGAN-IDS. IEEE Internet of Things Journal, 11, 15140–15151.

[9] Yang, X., Tong, F., Jiang, F., & Cheng, G. (2025). A lightweight and dynamic open-set intrusion detection for industrial internet of things. IEEE Transactions on Information Forensics and Security, 20, 2930–2943.

[10] Mirzaei, A., Coban, A. Z., Almgren, M., Aoudi, W., & Bertilsson, T. (2023). Scheduling to the rescue: Improving ML-based intrusion detection for IoT. In Proceedings of the 16th European Workshop on System Security (EuroSec ’23) (pp. 44–50). ACM.

[11] Fusco, P., Rimoli, G. P., & Ficco, M. (2024). TinyIDS — An IoT intrusion detection system by tiny machine learning. In Computational Science and Its Applications – ICCSA 2024 Workshops (pp. 71–82). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-65223-3_5

[12] National Institute of Standards and Technology. (2025). Ascon-based lightweight cryptography standards for constrained devices: Authenticated encryption, hash, and extendable output functions (NIST Special Publication 800-232). https://doi.org/10.6028/NIST.SP.800-232

[13] International Organization for Standardization & International Electrotechnical Commission. (2022). Cybersecurity — IoT security and privacy — Guidelines (ISO/IEC 27400:2022). ISO.