BIR SINFLI TAYANCH VEKTOR MASHINASI ASOSIDA TARMOQ HUJUMLARINI ANIQLASH MODELI
DOI:
https://doi.org/10.65164/pngqxk66Kalit so‘zlar:
bir sinfli tayanch vektor mashinasi, tarmoq hujumlari, model, anomaliyalarni aniqlash, kiberxavfsizlik, mashinali o‘qitish, normal trafik, xavfsizlik.Abstrak
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.
Havolalar
[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)
[10]. P. Nader, P. Honeine, P. Beauseroy, Intrusion detection in SCADA systems using one-class
classification. in 21st European Signal Processing Conference (EUSIPCO 2013) (IEEE, 2013)
[11]. 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)
[12]. S. Kaplantzis et al, Detecting selective forwarding attacks in wireless sensor networks using
support vector machines. in 2007 3rd International Conference on Intelligent Sensors, Sensor
321
Networks and Information (IEEE, 2007)
[13]. M. Amer, M. Goldstein, S. Abdennadher, Enhancing one-class support vector machines for
unsupervised anomaly detection. in Proceedings of the ACM SIGKDD Workshop on Outlier
Detection and Description (ACM, 2013)
[14]. P.Winter, E. Hermann, M. Zeilinger, Inductive intrusion detection in flow- based network data
using one-class support vector machines. in 2011 4th IFIP international conference on new
technologies, mobility and security (IEEE, 2011)
