BIR SINFLI TAYANCH VEKTOR MASHINASI ASOSIDA TARMOQ HUJUMLARINI ANIQLASH MODELI
Keywords:
bir sinfli tayanch vektor mashinasi, tarmoq hujumlari, model, anomaliyalarni aniqlash, kiberxavfsizlik, mashinali o‘qitish, normal trafik, xavfsizlikAbstract
Ruxsatsiz kirishni aniqlash usullarini o‘qitish uchun keng qamrovli va ishonchli ma’lumotlar to‘plamini topish, maxfiylik masalalari va mavjud ma’lumotlarning eskirganligi sababli jiddiy muammo hisoblanadi. Ushbu maqolada bir sinfli tayanch vektor mashinasi (OCSVM) algoritmini qo‘llaydigan yangi tarmoqqa ruxsatsiz kirishni aniqlash modeli taklif etiladi. Real vaqtdagi tarmoq trafigini Snort, Cowrie va Dionaea kabi sensorlar orqali yig‘ish uchun Zamonaviy honey tarmog‘i (MHN) tizimi joriy etildi. Eksperimental sozlamalar Google Cloud Ubuntu instansiyalari va ma’lumotlarga ishlov berish hamda modelni o‘qitish uchun Azure Machine Learning muhitini o‘z ichiga oladi. Natijalar shuni ko‘rsatadiki, taklif etilgan modelning umumiy aniqligi (Accuracy) 98.15% aniqlikka erishdi. Model samaradorligi umumiy aniqlik, aniqlik, to‘g‘rilik va F1 koeffitsiyenti metrikalari yordamida baholandi.
References
1. Usmanbayev D. Improving and evaluating methods network attack anomaly detection //2021 International Conference on Information Science and Communications Technologies (ICISCT). – IEEE, 2021. – С. 1-5.
2. Bozorov, Suhrobjon, and Doniyor Usmanbayev. Balanced ANN and majority based voting approach for building IDS. AIP Conference Proceedings. Vol. 3377. No. 1. AIP Publishing LLC, 2025.
3. Usmanbayev D. S. Kiberxavfsizlik: IT Infratuzilmasini Himoya Qilishning Zamonaviy Usullari //Green Economy and Development. – Т. 3. – №. 5. – С. 665738.
4. Mirpulatovich, K. M., Zakirovna, T. N., Gulnora, K., & Ismoilovna, U. D. S. (2019). Methodology for Developing a Mandatory Security Policy Based on Two Value Chains. Methodology, 6(11).
5. Shuxratovich, U. D. Kaspersky Threat Intelligence Services Analysis. Galaxy International Interdisciplinary Research Journal, 13(1), 90-93.
6. Shukhratovich, Usmanbayev D. Specific Features Of The Structure And Operation Of Network Attack Detection Systems. JournalNX, vol. 8, no. 04, 2022, pp. 224-228, doi:10.17605/OSF.IO/EYNQ2.
7. H.J. Liao et al., Intrusion detection system: a comprehensive review. J. Netw. Comput. Appl. 36(1), 16–24 (2013)
8. G. Giacinto, Intrusion detection in computer networks by a modular ensemble of one-class classifiers. Inf. Fusion 9(1), 69–82 (2008)
9. Inho Kang, Myong K. Jeong, Dongjoon Kong, A differentiated one-class classification method with applications to intrusion detection. Expert Syst. Appl. 39(4), 3899–3905 (2012)
11. A. Ghorbel, M. Snoussi, D. Abid, Online OCSVM for outlier detection based on the Coherence Criterion in Wireless Sensor Networks. in Proc International Conference. vol. 12 (2013)
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Usmanbayev Doniyorbek Shuxratovich
This work is licensed under a Creative Commons Attribution 4.0 International License.
