Streamlit ML Intrusion Detection System
A Streamlit web app that classifies network traffic as normal or anomalous with a Random Forest model trained on the NSL-KDD dataset.
Problem
Demonstrate an end-to-end machine-learning application - training, preprocessing, and an interactive web interface - for network intrusion detection.
Context
An educational ML project published as open source under the MIT license. The README reports dataset and performance figures that have not been independently reviewed, so none are repeated here.
The app wraps a scikit-learn Random Forest classifier in a Streamlit interface: a training script prepares the model on the NSL-KDD intrusion detection dataset, and the web UI classifies entered traffic features with confidence scores. It is a demonstration project on a synthetic benchmark dataset, not a validated security tool.