This project compared various machine and deep learning models in detecting cyberattacks based on network packet data. The models tested were:
- Support Vector Machines
- K-Nearest Neighbors
- Decision Trees
- Random Forests
- Gradient Boosted Trees
- Multilayer Perceptron Network (aka Dense Neural Network)
- Convolutional Neural Network
- Recurrent Neural Network
The dataset used is CIC-IDS2017 from the Canadian Institute for Cybersecurity, which can be found here.
The PowerPoint presentation in this repo contains a detailed writeup on each part of the project.
The Notebooks folder contains Jupyter Notebooks with the code I wrote for the project.