Enhancing Denial-of-Service (DoS) Attack Defense Mechanisms through Machine Learning-Based Analysis of Network Traffic Data

The purpose of this research project is to study the classification of normal and malicious network traffic (Denial-of Service; DoS) with a total of 5 machine learning models: Decision Tree, Random Forest, XGBoost, Support Vector Machine (SVM), and Convolutional Neural Network (CNN). The dataset that used for train the model named CSC-CIC-IDS2018, is a dataset about network traffics collected and created by the Canadian Institute for Cybersecurity (CIC), University of New Brunswick. The dataset contains 80 features. There are a total of 2,097,149 rows of data. And The Outcome after working process showed the model with highest F1-Score was the Convolutional Neural Network (CNN) model with a score of 0.998.