Machine Learning Approach for Intrusion Detection System to Mitigate Distributed Denial of Service Attack Based on Convolutional Neural Network Algorithm

Abstrak

Abstract— The rapid development of data communications alongside its nature to be protected and secured have resulted in a long on-going research and development of Intrusion Detection System (IDS). One of many approaches for improving IDS is by using Machine Learning (ML) method. This research proposes to build an IDS model using Convolutional Neural Network (CNN) algorithm which is a specialized type of ML. This research is conducted by converting CSE-CIC-IDS2018 samples into a pixelate image as an input to the IDS model to classify between benign and malicious network traffic. The best model will be chosen by comparing performance metrics of each model on different parameter combinations and the final model will be evaluated with k-fold Cross-validation technique to make sure the finest performance is obtained. The results obtained on this research are performance metrics scores that is higher than 93% for all of the parameter combinations. Based on the final result obtained, the authors concluded that the model proposed on this research is not only successful, but also is better compared to other traditional ML-based IDS in terms of performance metrics.
Keywords— Intrusion Detection System, Machine Learning, Convolutional Neural Network