DDoS Classification Using Neural Network and Naïve Bayes Methods for Network Forensics

Abstract

Distributed Denial of Service (DDoS) is a network security problem that continues to grow dynamically and has increased significantly to date. DDoS is a type of attack that is carried out by draining the available resources in the network by flooding the package with a significant intensity so that the system becomes overloaded and stops. This attack resulted in enormous losses for institutions and companies engaged in online services. Prolonged deductions and substantial recovery costs are additional losses for the company due to loss of integrity. The activities of damaging, disrupting, stealing data, and everything that is detrimental to the system owner on a computer network is an illegal act and can be imposed legally in court. Criminals can be punished based on the evidence found with the Forensics network mechanism. DDoS attack classification is based on network traffic activity using the neural network and naïve Bayes methods. Based on the experiments conducted, it was found that the results of accuracy in artificial neural networks were 95.23% and naïve Bayes were 99.9%. The experimental results show that the naïve Bayes method is better than the neural network. The results of the experiment and analysis can be used as evidence in the trial process.