Deep Ensemble-based Efficient Framework for Network Attack Detection

Drive Link

Full project available on Deep-Ensemble-Attack-Detection.

Project Overview

This project implements a Deep Ensemble-based Efficient Framework for detecting network attacks. By combining multiple machine learning models, this framework aims to improve the accuracy and robustness of network intrusion detection systems.

Features

• Real-time network attack detection using ensemble machine learning algorithms.
• Robust feature extraction and preprocessing.
• High accuracy and efficiency with deep learning models.
• Scalable to handle large-scale network data.

Technologies Used

• Python 3.6+
• Scikit-learn
• TensorFlow/Keras
• Pandas
• NumPy

System Design

System Design	Activity Diagram

---

Installation

Use Anaconda Navigator as base root

To install and run this project, follow these steps:

1. Download full project:
   Deep-Ensemble-Attack-Detection.

   cd Deep-Ensemble-Attack-Detection

2. Run the project:

   python app.py

Usage

1. Data Collection:

   • Predetermined and Trained KDD Datasets.
   • Tested and trained on 4-8 Lakhs of possibilites/datasets.
   • The application will analyze the data and predict the attack possibilites.

2. Homepage:

   • Access at LocalHost to predict threat detection and attack status.

---

Dataset

The dataset used for training and testing the machine learning models consists of network traffic data, including normal traffic and various network attack traffic.

Results

Project Snapshots

Homepage	Login
Prediction	Result