Makine Öğrenmesi ve Derin Öğrenme Teknikleri ile Saldırı Tespiti

Çalışır S., Atay R., Kurt Pehlivanoğlu M., Duru N.

4th International Conference on Computer Science and Engineering (UBMK-2019), Samsun, Türkiye, 11 - 15 Eylül 2019 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/ubmk.2019.8906997
  • Basıldığı Şehir: Samsun
  • Basıldığı Ülke: Türkiye
  • Anahtar Kelimeler: instrusion detection, DoS attacks, CIC DoS dataset, IDS, machine learning, deep learning, ATTACKS
  • Kocaeli Üniversitesi Adresli: Evet

Özet

Unlike traditional Denial of Service (DoS) attacks, application layer DoS attacks are nearly undetectable at the network layer. CIC DoS is one of the intrusion detection dataset which includes application layer DoS attacks. Therefore in this study, we handle this dataset to detect application based DoS attacks by using Random Forest, Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LGBM), Gradient Boosting, Multilayer Perceptron (MLP), Convolutional Neural Networks (CNN) and Support Vector Machine (SVM) algorithms. The experimental results show that the performance of the LGBM based model is better than the other algorithms.