☢️ The MiraiShield Project ☢️

[ Base Dataset ]	[ Project Proposal ]	[ Project Video ]	[ Project Page ]	[ Project Report ]

---

Overall Pipeline

---

Model Diagram

---

Model Stats

---

Hardware Flow and Implementation

---

---

Project Structure - Detecting IoT Botnet Attacks

├── README.md  
├── .idea                       
│    ├── .gitignore
│    ├── IoT-MiniProject.iml
│    ├── misc.xml
│    ├── modules.xml
│    ├── vcs.xml
│    └── inspectionProfiles
│       └── profiles_settings.xml
├── EDA                          # EDA, NAS and Self-Organising Maps
│    ├── bilinear.py
│    ├── features.py
│    ├── nas.py
│    └── som.py
├── Model_A                      # Base model #1
│    └── model.py
├── Model B                      # Base model #2
│    └── model.py
├── colab                        # Playground for notebooks
│    ├── IOT_IntrusionDetection_EDA_BaseModels.ipynb
│    └── Main_Model_DeepAE.ipynb
├── docs                         # Deploy docs
│    ├── _config.yml
│    ├── index.md
│    └── assets
│       ├── Figure_1.png
│       ├── IoTPipeline.png
│       ├── IoT_Botnet_models.png
│       ├── IoT_Botnet_models_new.png
│       ├── IoT_Modelkey.png
│       ├── abcd.png
│       ├── conf_C.png
│       ├── conf_D.png
│       ├── hardware.png
│       ├── hardware_mirai.png     
│       ├── repo_size.png
│       ├── repo_time.png
│       ├── size_plots.png
│       ├── time_plots.png   
│       └── r.jpeg
├── documentation                # Documentation of Project
│    ├── IoT Mini Project - Proposal.pdf
│    ├── IoT_Botnet_models.png
│    ├── IoT_Modelkey.png
│    ├── model2.png
│    └── nn.svg
├── Model_D                      # Proposed model - Attack Classifier
│    ├── test.py
│    └── train.py
├── hardware                     # Botnet Server and Socket Connections
│    ├── arduino.ino
│    ├── deepLearningCheck.py
│    └── mirai.py     
└── Model_C                      # Proposed model - Anomaly Detector
     ├── test.py
     └── train.py

---

Demo

We provide an easy-to-get-started demo using Google Colab!

This will allow you to train a basic version of our method using GPUs on Google Colab.

Description	Link
EDA Demo and Base Model Interactive Notebook

---

References

@misc{Dua:2019 ,
author = "Dua, Dheeru and Graff, Casey",
year = "2017",
title = "{UCI} Machine Learning Repository",
url = "http://archive.ics.uci.edu/ml",
institution = "University of California, Irvine, School of Information and Computer Sciences" }

---

@ARTICLE{8490192,  
author={Meidan, Yair and Bohadana, Michael and Mathov, Yael and Mirsky, Yisroel and Shabtai, Asaf and Breitenbacher, Dominik and Elovici, Yuval},  
journal={IEEE Pervasive Computing},   
title={N-BaIoT—Network-Based Detection of IoT Botnet Attacks Using Deep Autoencoders},   
year={2018},  
volume={17},  
number={3},  
pages={12-22},  
doi={10.1109/MPRV.2018.03367731}}