Intrusion Detection System using Machine Learning

Overview

This project implements various machine learning models for Intrusion Detection on the CICIDS2017 dataset. The dataset contains network traffic data and is used to train and evaluate different models for identifying network intrusions.

Models Implemented

Ensemble Models

• Random Forest Classifier

  • Implementation: RandomForest.ipynb
  • Description: This notebook contains the implementation of a Random Forest Classifier for intrusion detection.

• AdaBoost Classifier

  • Implementation: XGBoost.ipynb
  • Description: This notebook implements the AdaBoost classifier for detecting network intrusions.

Deep Learning Models

• Neural Network
  • Implementation: NeuralNetwork.ipynb
  • Description: This notebook contains the implementation of a simple neural network for intrusion detection.

Classic Machine Learning Models

• Logistic Regression

  • Implementation: LogisticRegression.ipynb
  • Description: This notebook contains the implementation of a Logistic Regression model for intrusion detection.

• K-Nearest Neighbors (KNN)

  • Implementation: KNN.ipynb
  • Description: This notebook implements the K-Nearest Neighbors algorithm for intrusion detection.

Dataset

The models are trained and evaluated on the CICIDS2017 dataset. You can download the dataset from here.