ML Network Intrusion Detection System

Overview

This project implements a Network Intrusion Detection System (NIDS) using various machine learning algorithms. The system is designed to classify network traffic as either normal or malicious (intrusion) based on features extracted from network packets.

Key Features

• Data Preprocessing: Handles missing values, encodes categorical variables, and scales numerical features.
• Model Selection: Compares performance of Random Forest, Support Vector Machines (SVM), and Logistic Regression.
• Real-time Detection: Capable of processing packet data streams for near real-time classification.
• Visualization: Includes confusion matrices and ROC curves to evaluate model performance.

Tech Stack

• Languages: Python
• Libraries: Scikit-learn, Pandas, NumPy, Matplotlib, Seaborn
• Tools: Jupyter Notebook

Performance

The Random Forest classifier achieved the highest accuracy of 99.2% on the validation set, with a low false positive rate.

Future Improvements

• Integration with deep learning models (CNN/RNN) for potentially better feature extraction.
• Deployment as a REST API for easier integration with existing network infrastructure.