GIBRID SUN’IY INTELLEKT ASOSIDA TARMOQ TRAFIGIDA KIBERHUJUMLARNI ANIQLASH: AUTOENCODER VA GRADIENT BOOSTING MODELI
Jo‘rayev N. N. & Juraboyev A. S.
Annotatsiya
Mazkur tadqiqotda tarmoq trafigida kiberhujumlarni aniqlash uchun gibrid sun’iy intellekt modeli taklif etiladi. Model ikki bosqichli arxitekturaga asoslanadi: birinchi bosqichda Autoencoder yordamida normal trafik xulq-atvori o‘rganilib, anomal holatlar aniqlanadi; ikkinchi bosqichda esa Gradient Boosting algoritmi yordamida aniqlangan anomaliyalar hujum turlariga tasniflanadi. Taklif etilgan yondashuv klassik IDS tizimlariga nisbatan yuqori aniqlik va past noto‘g‘ri signal (False Positive) ko‘rsatkichlarini ta’minlaydi. Tadqiqot natijalari modelning F1-score, ROC-AUC va aniqlik ko‘rsatkichlari bo‘yicha samaradorligini tasdiqlaydi. Ushbu model real vaqt rejimida ishlovchi kiberxavfsizlik tizimlariga integratsiya qilish uchun istiqbolli yechim sifatida baholanadi.
Adabiyotlar
- Goodfellow I., Bengio Y., Courville A. Deep Learning. – Cambridge: MIT Press, 2016. – 775 p.
- Bishop C. M. Pattern Recognition and Machine Learning. – New York: Springer, 2006. – 738 p.
- Hastie T., Tibshirani R., Friedman J. The Elements of Statistical Learning. – 2nd ed. – New York: Springer, 2009. – 745 p.
- Géron A. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow. – 2nd ed. – Sebastopol: O’Reilly Media, 2019. – 851 p.
- Chollet F. Deep Learning with Python. – 2nd ed. – New York: Manning Publications, 2021. – 504 p.
- Kelleher J. D., Namee B. M., D’Arcy A. Fundamentals of Machine Learning for Predictive Data Analytics. – Cambridge: MIT Press, 2015. – 624 p.
- Sommer R., Paxson V. Outside the closed world: On using machine learning for network intrusion detection // 2010 IEEE Symposium on Security and Privacy. – 2010. – P. 305–316.
- Lippmann R. et al. The 1999 DARPA intrusion detection evaluation dataset // MIT Lincoln Laboratory. – 2000.
- Sharafaldin I., Lashkari A. H., Ghorbani A. A. Toward generating a new intrusion detection dataset and intrusion traffic characterization (CIC-IDS2017) // ICISSP 2018. – 2018. – P. 108–116.
- Moustafa N., Slay J. UNSW-NB15: A comprehensive data set for network intrusion detection systems // Military Communications and Information Systems Conference (MilCIS). – 2015. – P. 1–6.
- Chen T., Guestrin C. XGBoost: A scalable tree boosting system // Proceedings of the 22nd ACM SIGKDD. – 2016. – P. 785–794.
- Ke G. et al. LightGBM: A highly efficient gradient boosting decision tree // Advances in Neural Information Processing Systems (NeurIPS). – 2017. – P. 3146–3154.
- Prokhorenkova L. et al. CatBoost: unbiased boosting with categorical features // Advances in Neural Information Processing Systems. – 2018. – P. 6638–6648.
- Sakurada M., Yairi T. Anomaly detection using autoencoders with nonlinear dimensionality reduction // Proceedings of MLSDA 2014. – 2014. – P. 4–11.
- Hinton G. E., Salakhutdinov R. R. Reducing the dimensionality of data with neural networks // Science. – 2006. – Vol. 313. – P. 504–507.
- McNemar Q. Note on the sampling error of the difference between correlated proportions or percentages // Psychometrika. – 1947. – Vol. 12. – P. 153–157.
- Fawcett T. An introduction to ROC analysis // Pattern Recognition Letters. – 2006. – Vol. 27. – P. 861–874.
- Saito T., Rehmsmeier M. The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets // PLoS ONE. – 2015. – Vol. 10(3). – e0118432.
- Alpaydin E. Introduction to Machine Learning. – 4th ed. – Cambridge: MIT Press, 2020. – 640 p.
- Scikit-learn: Machine Learning in Python // Pedregosa F. et al. Journal of Machine Learning Research. – 2011. – Vol. 12. – P. 2825–2830.