Detecting Denial of Service attacks using machine learning algorithms

Abstract

Currently, Distributed Denial of Service Attacks are the most dangerous cyber danger. By inhibiting the server's ability to provide resources to genuine customers, the affected server's resources, such as bandwidth and buffer size, are slowed down. A mathematical model for distributed denial-of-service attacks is proposed in this study. Machine learning algorithms such as Logistic Regression and Naive Bayes, are used to detect attacks and normal scenarios. The CAIDA 2007 Dataset is used for experimental study. The machine learning algorithms are trained and tested using this dataset and the trained algorithms are validated. Weka data mining platform are used in this study for implementation and results of the same are analysed and compared. Other machine learning algorithms used with respect to denial of service attacks are compared with the existing work.