Project Data Protection

The objective of this project is to apply the data analysis chain on a cyberphysical dataset:

1. Using only network data
2. Using only physical data

Compare different algorithms (KNN, CART, Random Forest, XGBoost, MLP...)

Build a streamlit webapp providing an interactive interface to explore results.

Installation

With Conda

Create a new environment :

conda env create -f environment.yaml

Activate the environment :

conda activate data_protection

With pip

pip install -r requirements.txt

Run streamlit app

Il faut lancer les notebook pour générer les datas clean avant (clean_network_attacks.ipynb / clean_network_attacks.ipynb)

streamlit run web/streamlit_app_physical.py

streamlit run web/streamlit_app_network.py

Resources

• Download all the data from here