Optimizing Performance Random Forest Algorithm Using Correlation-Based Feature Selection (CFS) Method to Improve Distributed Denial of Service (DDoS) Attack Detection Accuracy

Abstract

In the ever-evolving digital era, Distributed Denial of Service (DDoS) attacks have become a major threat to the security of networks and online services, making it important to develop effective strategies to detect and overcome such attacks.This research aims to improve the performance of Random Forest algorithm in dealing with DDoS attacks by using Correlation-Based Feature Selection method. This method can identify and select the most relevant features from the dataset used, in this case the CIC-DDoS2019 dataset, with respect to accuracy, precision, recall, and F1-score as evaluation metrics, so that this research achieves the best results in effectively detecting and preventing DDoS attacks, making an important contribution in strengthening the security of networks and online services.The results show that the application of the Correlation-Based Feature Selection method is able to improve DDoS attack detection in a complex network context using the Random Forest algorithm, increasing the detection accuracy rate to 99.89%. These findings highlight the potential of using the Random Forest algorithm with the CFS method in improving DDoS attack detection in complex network environments.This study recorded a significant improvement compared to the previous study, which only achieved an accuracy rate of 99.7% using the feature importance method.