Machine Learning for Network Intrusion Detection System

• Started on: Oct.07 2022
• Finished on: Dec. 05 2022

Context

This project takes place in the Machine Learning Course followed in Dalhousie University, in Halifax, Canada. The objective of this project is to compare different machine learning algorithms effectiveness to power a Network-Based Intrusion Detection System.

Authors

• Corentin Goetghebeur
• Gabriel Marchand
• Rinchen Toh

Dataset

This project is based on the KDDcup'99 dataset, a network traffic dataset widely used for research and acedemic purposes.

Algorithms

For this project, we compared the foolowing algorithms:

• Naive Bayes
• Logistic Regression
• Support Vector Machine
• K-Nearest Neighbors
• Random Forest
• Decision Tree

Report

For more information see the full project report and the powerpoint presentation.