UNSW-NB15 DATASETIDA TARMOQ HUJUMLARINI MASHINALI O'QITISH BILAN TOIFALASH: RANDOM FOREST VA XGBOOST MODELLARINI TAQQOSLASH VA CHEGARA SEZGIRLIGI TAHLILI
Keywords:
hujumlarni aniqlash tizimi, UNSW-NB15, Random Forest, XGBoost, soxta signallar, chegara sezgirligi.Abstract
UNSW-NB15 datasetining standart train/test bo'linmasida Random Forest, XGBoost va bazaviy Logistic Regression modellari tarmoq hujumlarini ikki sinfli toifalash masalasida taqqoslandi. Har bir model 5 marta turli tasodifiy parametr bilan o'qitildi. XGBoost eng yuqori F1 (0,896) va ROC-AUC (0,984) ko'rsatdi, Random Forest'dan (F1 0,894) farq kichik bo'ldi, lekin XGBoost taxminan 6 baravar tez o'qitildi. Barcha modellarda recall yuqori (0,97-0,99), soxta signallar ulushi (FPR) esa 0,26-0,40 bo'ldi. XGBoost chegarasini 0,5 dan 0,9 ga ko'tarish FPR'ni 0,261 dan 0,037 ga tushirdi, recall esa 0,984 dan 0,905 ga kamaydi. Natijalar bitta datasetda va bitta bo'linmada olingan, shuning uchun dastlabki hisoblanadi.
References
1. Ali A. H., Charfeddine M., Ammar B., Ben Hamed B., Albalwy F., Alqarafi A., Hussain A. Unveiling machine learning strategies and considerations in intrusion detection systems: a comprehensive survey. Frontiers in Computer Science, 2024, 6. DOI: 10.3389/fcomp.2024.1387354.
2. Mohammed I. M., Aljanabi M., Muhialdeen H. M. Systematic literature review on intrusion detection systems: Research trends, algorithms, methods, datasets, and limitations. Journal of Intelligent Systems, 2024, 33(1). DOI: 10.1515/jisys-2023-0248.
3. Sowmya T., Mary Anita E. A. A comprehensive review of AI based intrusion detection system. Measurement: Sensors, 2023, 28.
4. Tripathy S. S., Behera B. A Review of Various Datasets for Machine Learning Algorithm-Based Intrusion Detection System: Advances and Challenges. arXiv:2506.02438, 2025.
5. Ndichu S., Ban T., Ozawa S., Takahashi T., Inoue D. AI-Driven Security Alert Screening and Alert Fatigue Mitigation in Security Operations Centers: A Survey. arXiv:2605.08316, 2026 (preprint).
6. Moustafa N., Slay J. UNSW-NB15: a comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set). Military Communications and Information Systems Conference (MilCIS), 2015.
7. Moustafa N., Slay J. The evaluation of Network Anomaly Detection Systems: Statistical analysis of the UNSW-NB15 dataset and the comparison with the KDD99 dataset. Information Security Journal: A Global Perspective, 2016, 1-14. [UNSW sahifasi yana uchta ishni keltirishni talab qiladi, ularni sahifadan qo'shing.]
8. Breiman L. Random Forests. Machine Learning, 2001, 45(1), 5-32.
9. Chen T., Guestrin C. XGBoost: A Scalable Tree Boosting System. Proc. 22nd ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, 2016, pp. 785-794.
10. Pedregosa F. et al. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 2011, 12, 2825-2830.
