Evaluation DDoS attack detection through the application of machine learning techniques on the CICIDS2017 dataset in the field of information security
Yükleniyor...
Dosyalar
Tarih
2023
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
International Information and Engineering Technology Association
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
Amongst network and Intrusion Detection System (IDS) threats, Distributed Denial of Service (DDoS) attacks often take precedence due to their significant potential to disrupt services, leading to financial and reputational damages for organizations. This study employs eight advanced machine learning techniques to distinguish between two types of DDoS attacks: DoS Hulk and DoS Slow HTTP Test. The applied algorithms include Decision Tree (DT), Random Forest (RF), Gradient Boosting (GB), AdaBoost, Naive Bayes (NB), Extreme Gradient Boosting (XGB), Ridge regression, and Multilayer Perceptron (MLP). Utilizing a Python environment, these methods were applied to the DDoS attacks in the CICIDS2017 dataset for classification into benign or DoS categories across two distinct experiments. The results were highly encouraging: The first experiment achieved an accuracy rate exceeding 99%, while the second experiment achieved a perfect success rate of 100%. These findings outperform those of previous studies in terms of their efficiency, demonstrating the potential of these machine learning techniques in enhancing DDoS attack detection.
Açıklama
Anahtar Kelimeler
Algorithms, DoS attacks, IDS threats, Python environment
Kaynak
Mathematical Modelling of Engineering Problems
WoS Q Değeri
Scopus Q Değeri
Q3
Cilt
10
Sayı
4
Künye
Ahmed, A. S., Kurnaz, S., & Khaleel, A. M. (2023). Evaluation DDoS attack detection through the application of machine learning techniques on the CICIDS2017 dataset in the field of information security. Mathematical Modelling of Engineering Problems, 10(4), 1125-1134.
