aaaastark/intrusion-detection-system-mqtt-enabled-iot

Intrusion Detection System for MQTT Enabled IoT.

Research Paper: A Deep Learning-Based Intrusion Detection System for MQTT Enabled IoT

Get Started with Relevant Project Implementation

• If you're looking for assistance with a project implementation that aligns with your needs, feel free to get in touch with us LinkedIn.
• To get in touch with us and discuss your project implementation needs, please send an email to [email protected].
• Thank you for considering our services. We look forward to working with you!

In this thesis, we proposed a Artificial Neural Network (ANN) for intrusion detection in the MQTT-based protocol and also compared its performance with other traditional machine learning (ML) algorithms, such as a Deep Neural Network (DNN), Naive Bayes (NB), Random Forest (RF), k-Nearest Neighbour (kNN), Decision Tree (DT), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRUs). The performance is proved using publicly available datasets, including MQTT-IoTIDS2020. The MQTT-IoT-IDS2020 contains three abstract-level features, including Uni-Flow, Bi-Flow, and Packet-Flow. The results for the first dataset and binary classification show that the ANN-based model achieved 99.79%, 99.85%, and 94.36% accuracies for Uni-flow, Bi-flow, and Packet-flow, respectively. However, in the case of multi-label classification, these accuracies reduced to 99.71%, 99.70%, and 92.86%, respectively.

Research Paper: A Deep Learning-Based Intrusion Detection System for MQTT Enabled IoT

• Website Link for Paper: https://www.researchgate.net/publication/355478103_A_Deep_Learning-Based_Intrusion_Detection_System_for_MQTT_Enabled_IoT.

Loading the dataset IEEE DataPort (MQTT-IOT-IDS2020)

• Website Link for Dataset: https://ieee-dataport.org/open-access/mqtt-iot-ids2020-mqtt-internet-things-intrusion-detection-dataset.
• 

MQTT INTERNET OF THINGS INTRUSION DETECTION DATASET

Workflow that is used in this Project

• Data Processing
• Data Normalization
• Binary Class Classification
• Multi Class Classification
• Feature Extraction (BC and MC)
• Artificial Neural Network Model (ANN)
• Visualization Accuracy and Loss
• Classification Report
• Mean Absolute Error, Mean Squared Error, Root Mean Squared Error, and R2 Score

APIs that are used in this Project

• tensorflow
• sklearn
• keras
• matplotlib
• numpy
• pandas

Paper vs Proposed Results: DNN vs ANN netowrks

Binary Class Classification

• Bi-flow Features Paper: 99.75%

• Bi-flow Features Proposed: 99.85%

• 

• 

• 

• Ui-flow Features Paper: 99.92%

• Ui-flow Features Paper: 99.79%

• 

• 

• 

• Packet-flow Features Paper: 94.94%

• Packet-flow Features Paper: 94.36%

• 

• 

• 

Multi Class Classification

• Bi-flow Features Paper: 98.12%

• Bi-flow Features Proposed: 99.70%

• 

• 

• 

• Ui-flow Features Paper: 97.08%

• Ui-flow Features Paper: 99.71%

• 

• 

• 

• Packet-flow Features Paper: 90.79%

• Packet-flow Features Paper: 92.86%

• 

• 

•