Usage of Machine Learning in DDOS Attack Detection

Adilzhan Slyamkhanov, Zhanybek Bozbayev, Ayym Alzhanova, Artur Pan, Temirlan Ramazan, Leila Rzayeva

2023

Closed access Metadata (CSL-JSON)
DOI 10.1109/wincom59760.2023.10322885
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

In this article, the best model for determining DDoS attacks using machine learning algorithms is proposed. During the research work, models were built using algorithms such as RFC (Random Forest Classifier), Logistic Regression, SVM (Support Vector Machine), KNN (k-Nearest Neighbor) and Decision Tree Classifier. A comparative analysis of each model was carried out with the reduction of their metrics, as a result of which the model with the best results was selected, showing the accuracy of the tests at 0.9995.