Skip to content

[Anomaly detection] refers to the process of identifying patterns in data that do not conform to expected behavior. This project aims to develop a machine learning model to predict and identify potential attacks in IoT networks, thus helping to secure these networks from malicious activities.

Notifications You must be signed in to change notification settings

gaurav-borse/anamoly-detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Anamoly Detection | About Us

About the Anomaly Detection App

Who We Are - Find Out About Our Team and Vision.


Project Overview

In today's connected world, IoT (Internet of Things) networks are increasingly becoming targets for cyber-attacks. This project aims to develop a machine learning model to predict and identify potential attacks in IoT networks, thus helping to secure these networks from malicious activities.

Functionality

This application provides the following key functionalities:

1. Dataset Display

  • The application displays two primary datasets: KDDTrain+.txt and KDDTest+.txt.
  • These datasets are used to train and test the anomaly detection model.
  • You can view the structure and content of these datasets on the Dataset Display page.

2. Anomaly Detection

  • Users can input various features of network traffic to predict whether the traffic is normal or an attack.
  • The model classifies attacks into different categories such as DOS, Probe, U2R, and Sybil.

3. Model Evaluation

  • The application provides metrics such as accuracy, precision, and recall to evaluate the performance of the model.
  • Users can see how well the model performs in distinguishing between normal and malicious network traffic.

4. Visualization

  • The project includes various visualizations to help understand the data and the model's performance.
  • These visualizations include confusion matrices and other relevant charts.

Vision

Our vision is to create a robust and efficient system for detecting anomalies in IoT networks, ensuring the security and integrity of connected devices. By leveraging machine learning, we aim to provide a tool that can help in early detection and prevention of cyber-attacks, thus safeguarding sensitive information and maintaining the smooth operation of IoT systems.

Team

  • Gaurav Borse
  • Shubham Thorat
  • Urmila Narvade
  • Vaishnavi Pratale

Technical Details

  • Programming Language: Python
  • Framework: Streamlit for the frontend, scikit-learn for machine learning
  • Datasets: KDDTrain+.txt and KDDTest+.txt, which are standard datasets used for network intrusion detection.

Contact Us

If you have any questions or suggestions, please contact us at [gborse108@gmail.com].

For more details, visit our GitHub repository.


Steps to run

Watch the tutorial video

How to Make a Multi-Page Web App | Streamlit #16

How to Make a Multi-Page Web App | Streamlit #16

Demo Video

Launch the web app:

[See Now

Commands

Reproducing this web app

To recreate this web app on your own computer, do the following.

Create conda environment

Firstly, we will create a conda environment called multipage

conda create -n multipage python=3.7.9

Secondly, we will login to the multipage environement

conda activate multipage

Install prerequisite libraries

Download requirements.txt file

wget https://raw.githubusercontent.com/dataprofessor/ml-auto-app/main/requirements.txt

Pip install libraries

pip install -r requirements.txt

Download and unzip this repo

Download this repo and unzip as your working directory.

Launch the app

streamlit run app.py

Output

alt text

alt text

alt text

alt text

alt text

alt text

alt text

About

[Anomaly detection] refers to the process of identifying patterns in data that do not conform to expected behavior. This project aims to develop a machine learning model to predict and identify potential attacks in IoT networks, thus helping to secure these networks from malicious activities.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published