TARMOQ TRAFIGIDAGI KIBERHUJUMLARNI ANIQLASHDA MASHINALI O‘QITISH ALGORITMLARINI TAQQOSLASH: PAST KECHIKISH VA NOTO‘G‘RI TREVOGA MUAMMOLARI

Samarov X. K., Surayyo R. B. & Xaitbayev A. P.


Annotatsiya

Ushbu maqolada tarmoq trafigidagi DoS, Probe, U2R va R2L kiberhujumlarini aniqlashda mashinali o‘qitish algoritmlarining qiyosiy tahlili keltirilgan. Isolation Forest, Autoencoder, XGBoost, Random Forest, SVM va LSTM algoritmlari aniqlik, F1-o‘lchov, kechikish vaqti va noto‘g‘ri trevoga darajasi bo‘yicha NSL-KDD ma'lumotlar to‘plami asosida baholangan. XGBoost 97–99% aniqlik va 3 ms dan past kechikish bilan eng maqbul yechim sifatida aniqlangan. Noto‘g‘ri trevoga darajasini kamaytirish uchun xususiyatlarni tanlash, chegaraviy qiymatni optimallashtirish, kaskadli ansambl tasniflash va SMOTE usullari tavsiya etiladi. Tadqiqot natijalari real vaqtli kiberhujumlarni aniqlash tizimlarini loyihalash uchun amaliy ko‘rsatmalar beradi.


Adabiyotlar

  1. Buczak A. L., Guven E. A survey of data mining and machine learning methods for cyber security intrusion detection // IEEE Communications Surveys & Tutorials. — 2016. — Vol. 18, No. 2. — P. 1153–1176.
  2. Tavallaee M., Bagheri E., Lu W., Ghorbani A. A detailed analysis of the KDD CUP 99 data set // Proc. IEEE Symposium on Computational Intelligence for Security and Defense Applications (CISDA). — Ottawa, Canada. — 2009. — P. 1–6.
  3. Shone N., Ngoc T. N., Phai V. D., Shi Q. A deep learning approach to network intrusion detection // IEEE Transactions on Emerging Topics in Computational Intelligence. — 2018. — Vol. 2, No. 1. — P. 41–50.
  4. Agrawal S., Agrawal J. Survey on anomaly detection using data mining techniques // Procedia Computer Science. — 2015. — Vol. 60. — P. 708–713.
  5. Liu F. T., Ting K. M., Zhou Z. H. Isolation Forest // Proc. 8th IEEE International Conference on Data Mining (ICDM). — Pisa, Italy. — 2008. — P. 413–422.
  6. An J., Cho S. Variational autoencoder based anomaly detection using reconstruction probability // Special Lecture on IE. — Seoul, South Korea. — 2015. — Vol. 2, No. 1. — P. 1–18.
  7. Chen T., Guestrin C. XGBoost: A scalable tree boosting system // Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. — San Francisco, USA. — 2016. — P. 785–794.