Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Sensor Driven Resource Optimization Framework for Intelligent Fog Enabled IoHT Systems.

Sensors (Basel, Switzerland)·2026
Same author

Aerial Imaging-Based Soiling Detection System for Solar Photovoltaic Panel Cleanliness Inspection.

Sensors (Basel, Switzerland)·2025
Same author

Stabilized quantum-enhanced SIEM architecture and speed-up through Hoeffding tree algorithms enable quantum cybersecurity analytics in botnet detection.

Scientific reports·2024
Same author

Robust Epileptic Seizure Detection Using Long Short-Term Memory and Feature Fusion of Compressed Time-Frequency EEG Images.

Sensors (Basel, Switzerland)·2023
Same author

BeepTrace: Blockchain-Enabled Privacy-Preserving Contact Tracing for COVID-19 Pandemic and Beyond.

IEEE internet of things journal·2023
Same author

AALLA: Attack-Aware Logical Link Assignment Cost-Minimization Model for Protecting Software-Defined Networks against DDoS Attacks.

Sensors (Basel, Switzerland)·2023

Related Experiment Video

Updated: Oct 13, 2025

Data Communication Based on MQTT in a Polymer Extrusion Process
08:15

Data Communication Based on MQTT in a Polymer Extrusion Process

Published on: July 15, 2022

3.6K

A Deep Learning-Based Intrusion Detection System for MQTT Enabled IoT.

Muhammad Almas Khan1, Muazzam A Khan1, Sana Ullah Jan2

  • 1Department of Computer Sciences, Quaid-i-Azam University, Islamabad 44000, Pakistan.

Sensors (Basel, Switzerland)
|November 13, 2021
PubMed
Summary

A Deep Neural Network (DNN) effectively detects intrusions in Message Queuing Telemetry Transport (MQTT) IoT networks. The DNN model significantly outperforms traditional machine learning algorithms in identifying various cyberattacks.

Keywords:
IDSIoTMQTTclassificationsecurity

More Related Videos

A Precise and Autonomous System for the Detection of Insect Emergence Patterns
06:22

A Precise and Autonomous System for the Detection of Insect Emergence Patterns

Published on: January 9, 2019

5.8K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.4K

Related Experiment Videos

Last Updated: Oct 13, 2025

Data Communication Based on MQTT in a Polymer Extrusion Process
08:15

Data Communication Based on MQTT in a Polymer Extrusion Process

Published on: July 15, 2022

3.6K
A Precise and Autonomous System for the Detection of Insect Emergence Patterns
06:22

A Precise and Autonomous System for the Detection of Insect Emergence Patterns

Published on: January 9, 2019

5.8K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.4K

Area of Science:

  • Cybersecurity
  • Network Protocols
  • Machine Learning

Background:

  • Internet of Things (IoT) devices utilize diverse messaging protocols, with Message Queuing Telemetry Transport (MQTT) being prevalent for sensor data.
  • The publish-subscribe model of MQTT presents security vulnerabilities, increasing susceptibility to various cyberattacks.
  • Intrusion detection is critical for securing IoT environments against threats like Man in the Middle (MitM), network intrusions, and Denial of Services (DoS).

Purpose of the Study:

  • To propose and evaluate a Deep Neural Network (DNN) model for intrusion detection in MQTT-based IoT communication.
  • To compare the performance of the proposed DNN model against traditional machine learning algorithms.

Main Methods:

  • Developed a Deep Neural Network (DNN) model for intrusion detection.
  • Evaluated the DNN model on two distinct datasets: MQTT-IoT-IDS2020 and a dataset featuring MitM, network intrusion, and DoS attacks.
  • Compared DNN performance against Naive Bayes (NB), Random Forest (RF), k-Nearest Neighbour (kNN), Decision Tree (DT), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRUs).

Main Results:

  • For the MQTT-IoT-IDS2020 dataset (binary classification), the DNN achieved accuracies of 99.92% (Uni-Flow), 99.75% (Bi-Flow), and 94.94% (Packet-Flow).
  • In multi-label classification on the same dataset, accuracies were 97.08% (Uni-flow), 98.12% (Bi-flow), and 90.79% (Packet-flow).
  • Against LSTM and GRUs on the second dataset, the DNN model achieved a highest accuracy of 97.13%.

Conclusions:

  • The proposed DNN model demonstrates superior performance in detecting intrusions within MQTT-based IoT networks.
  • DNNs offer a robust solution for enhancing the security of IoT communications against sophisticated cyber threats.
  • The study highlights the effectiveness of DNNs over traditional ML algorithms for MQTT intrusion detection.