Detection DDOS attacks using machine learning methods

Wishing to communicate with each other of people contributes to improving technology, and it has made the internet concept an indispensable part of our daily life. Cyber attacks from extranets to enterprise networks or intranets, which are used as personal, can cause pecuniary loss and intangible damage. It is critical to take due precautions for minimizing the losses by early detection of attacks. This study aims to analyze the rate of success in the intrusion detection system by using different methods. In this study, the CICDDoS2019 data set has been used, and DDOS attacks in this data set were compared. The success rates of threat determination were analyzed as using Artificial Neural Networks (ANN), Support Vector Machine (SVM), Gaussian Naive Bayes, Multinomial Naive Bayes, Bernoulli Naive Bayes, Logistic Regression, K-nearest neighbor (KNN), Decision Tree (entropy-gini) and Random Forest algorithms. It has been seen that the highest of the success rate is the models that ensure almost 100% success that was made by using K-nearest neighbor, Logistic Regression, Naive Bayes, (Multinomial - Bernoulli algorithms).