Simple Yet Powerful Machine Learning Based IoT Intrusion System With Smart Preprocessing and Feature Generation Rivals Deep Learning

Project Code :TCPGPY2080

Objective

The primary objective of this project is to develop a machine learning-based intrusion detection system that effectively detects and classifies IoT network attacks. By leveraging the UNSW-NB15 dataset, this project aims to train and evaluate a variety of machine learning models, such as Decision Tree, Random Forest, XGBoost, and Convolutional Neural Networks, to detect attack types including DoS, Exploits, and Worms. The system will integrate these models into a user-friendly web application, developed using Flask, HTML, CSS, and JavaScript, where users can input data and predict the type of attack. Additionally, an alert email system will be implemented to notify administrators immediately upon detection of an attack, enabling a quick response. The project will also focus on feature preprocessing to enhance model accuracy, offering an efficient solution for IoT network security.

Abstract

This project develops an IoT intrusion detection system using machine learning to identify attacks within IoT networks. Leveraging the UNSW-NB15 dataset, the system classifies attacks into categories like DoS, Exploits, Reconnaissance, and more. It uses models such as Decision Tree, Random Forest, XGBoost, LightGBM, AdaBoost, ANN, and CNN for attack classification. The system incorporates advanced preprocessing to improve model accuracy. Additionally, an alert email feature is integrated to notify administrators immediately upon detecting an attack, enhancing the real-time response capabilities. The backend handles model training and prediction, while the frontend, built with Flask, HTML, CSS, and JavaScript, offers an intuitive interface for users to input data and predict attack types, providing an effective solution for IoT network security.

Keywords: IoT Intrusion Detection, Machine Learning, UNSW-NB15 Dataset, Attack Classification, DoS, Exploits, Generic, Normal, Reconnaissance, Shellcode, Worms, Decision Tree, Random Forest, XGBoost, LightGBM, AdaBoost, Artificial Neural Networks, Convolutional Neural Networks, Feature Preprocessing, Flask, Web Application, Frontend Development, Alert System, Email Notification.

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.