DDOS HUJUMLARINI ANIQLASHDA MASHINALI O'QITISH ALGORITMLARINING QIYOSIY TAHLILI: RANDOM FOREST, KNN, XGBOOST VA LIGHTGBM
DOI:
https://doi.org/10.65164/c52tb643Kalit so‘zlar:
DDoS hujumlari, Random Forest, KNN, XGBoost, LightGBM, mashinali o'qitish, tarmoq xavfsizligi, hisoblash samaradorligi, intrusion detection.Abstrak
Ushbu maqolada uchta xalqaro benchmark dataset (CIC-DDoS2019, UNSWNB15,
Network Intrusion) asosida to'rtta mashinali o'qitish algoritmi — Random Forest (RF), KNearest
Neighbors (KNN), XGBoost va LightGBM — ning DDoS hujumlarini aniqlashdagi
samaradorligi qiyosiy tahlil qilinadi. Algoritmlar nafaqat aniqlik (accuracy, F1-score), balki hisoblash
samaradorligi (o'qitish va bashorat vaqti) bo'yicha ham baholandi. Tajribalar shuni ko'rsatdiki,
XGBoost CIC-DDoS2019 datasetida eng yuqori aniqlikka (93.47%) erishdi, LightGBM esa
Network-Intrusion datasetida 99.92% natija ko'rsatdi. Hisoblash samaradorligi tahlili Random Forest
algoritmining 88.4–687.9 ms bashorat vaqti bilan real vaqt DDoS aniqlash tizimi uchun eng maqbul
variant ekanligini isbotladi. KNN ning 8,000–10,000 ms bashorat vaqti esa real vaqt tizimlarida
qo'llash uchun yaroqsiz ekanligi aniqlandi.
Havolalar
[1]. M. Waqas et al., "A Systematic Review of DDoS Attack Detection Techniques," IEEE Access,
vol. 10, pp. 45891–45924, 2022.
[2]. N. Farnaaz and M. A. Jabbar, "Random Forest Modeling for Network Intrusion Detection
System," Procedia Computer Science, vol. 89, pp. 213–217, 2016.
[3]. Sharafaldin et al., "Toward Generating a New Intrusion Detection Dataset," in Proc. ICISSP,
2018, pp. 108–116.
[4]. N. Moustafa and J. Slay, "UNSW-NB15: A Comprehensive Data Set for Network Intrusion
Detection Systems," in Proc. MilCIS, 2015.
[5]. J. Zhang et al., "Random-Forests-Based Network Intrusion Detection Systems," IEEE Trans.
Systems, Man, Cybernetics, vol. 38, no. 5, pp. 649–659, 2008.
[6]. T. Chen and C. Guestrin, "XGBoost: A Scalable Tree Boosting System," in Proc. KDD, 2016,
pp. 785–794.
