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

A large number of smart devices in Internet of Things (IoT) environments communicate via different messaging protocols. Message Queuing Telemetry Transport (MQTT) is a widely used publish–subscribe-based protocol for the communication of sensor or event data. The publish–subscribe strategy makes it...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Muhammad Almas Khan, Muazzam A. Khan, Sana Ullah Jan, Jawad Ahmad, Sajjad Shaukat Jamal, Awais Aziz Shah, Nikolaos Pitropakis, William J. Buchanan
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
IDS
IoT
Acceso en línea:https://doaj.org/article/6ffba6c808314d33a4c1320a4aa27ea1
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:6ffba6c808314d33a4c1320a4aa27ea1
record_format dspace
spelling oai:doaj.org-article:6ffba6c808314d33a4c1320a4aa27ea12021-11-11T19:03:12ZA Deep Learning-Based Intrusion Detection System for MQTT Enabled IoT10.3390/s212170161424-8220https://doaj.org/article/6ffba6c808314d33a4c1320a4aa27ea12021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7016https://doaj.org/toc/1424-8220A large number of smart devices in Internet of Things (IoT) environments communicate via different messaging protocols. Message Queuing Telemetry Transport (MQTT) is a widely used publish–subscribe-based protocol for the communication of sensor or event data. The publish–subscribe strategy makes it more attractive for intruders and thus increases the number of possible attacks over MQTT. In this paper, we proposed a Deep Neural Network (DNN) for intrusion detection in the MQTT-based protocol and also compared its performance with other traditional machine learning (ML) algorithms, such as a 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 two different publicly available datasets, including (1) MQTT-IoT-IDS2020 and (2) a dataset with three different types of attacks, such as Man in the Middle (MitM), Intrusion in the network, and Denial of Services (DoS). 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 DNN-based model achieved 99.92%, 99.75%, and 94.94% accuracies for Uni-flow, Bi-flow, and Packet-flow, respectively. However, in the case of multi-label classification, these accuracies reduced to 97.08%, 98.12%, and 90.79%, respectively. On the other hand, the proposed DNN model attains the highest accuracy of 97.13% against LSTM and GRUs for the second dataset.Muhammad Almas KhanMuazzam A. KhanSana Ullah JanJawad AhmadSajjad Shaukat JamalAwais Aziz ShahNikolaos PitropakisWilliam J. BuchananMDPI AGarticleMQTTIDSIoTsecurityclassificationChemical technologyTP1-1185ENSensors, Vol 21, Iss 7016, p 7016 (2021)
institution DOAJ
collection DOAJ
language EN
topic MQTT
IDS
IoT
security
classification
Chemical technology
TP1-1185
spellingShingle MQTT
IDS
IoT
security
classification
Chemical technology
TP1-1185
Muhammad Almas Khan
Muazzam A. Khan
Sana Ullah Jan
Jawad Ahmad
Sajjad Shaukat Jamal
Awais Aziz Shah
Nikolaos Pitropakis
William J. Buchanan
A Deep Learning-Based Intrusion Detection System for MQTT Enabled IoT
description A large number of smart devices in Internet of Things (IoT) environments communicate via different messaging protocols. Message Queuing Telemetry Transport (MQTT) is a widely used publish–subscribe-based protocol for the communication of sensor or event data. The publish–subscribe strategy makes it more attractive for intruders and thus increases the number of possible attacks over MQTT. In this paper, we proposed a Deep Neural Network (DNN) for intrusion detection in the MQTT-based protocol and also compared its performance with other traditional machine learning (ML) algorithms, such as a 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 two different publicly available datasets, including (1) MQTT-IoT-IDS2020 and (2) a dataset with three different types of attacks, such as Man in the Middle (MitM), Intrusion in the network, and Denial of Services (DoS). 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 DNN-based model achieved 99.92%, 99.75%, and 94.94% accuracies for Uni-flow, Bi-flow, and Packet-flow, respectively. However, in the case of multi-label classification, these accuracies reduced to 97.08%, 98.12%, and 90.79%, respectively. On the other hand, the proposed DNN model attains the highest accuracy of 97.13% against LSTM and GRUs for the second dataset.
format article
author Muhammad Almas Khan
Muazzam A. Khan
Sana Ullah Jan
Jawad Ahmad
Sajjad Shaukat Jamal
Awais Aziz Shah
Nikolaos Pitropakis
William J. Buchanan
author_facet Muhammad Almas Khan
Muazzam A. Khan
Sana Ullah Jan
Jawad Ahmad
Sajjad Shaukat Jamal
Awais Aziz Shah
Nikolaos Pitropakis
William J. Buchanan
author_sort Muhammad Almas Khan
title A Deep Learning-Based Intrusion Detection System for MQTT Enabled IoT
title_short A Deep Learning-Based Intrusion Detection System for MQTT Enabled IoT
title_full A Deep Learning-Based Intrusion Detection System for MQTT Enabled IoT
title_fullStr A Deep Learning-Based Intrusion Detection System for MQTT Enabled IoT
title_full_unstemmed A Deep Learning-Based Intrusion Detection System for MQTT Enabled IoT
title_sort deep learning-based intrusion detection system for mqtt enabled iot
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/6ffba6c808314d33a4c1320a4aa27ea1
work_keys_str_mv AT muhammadalmaskhan adeeplearningbasedintrusiondetectionsystemformqttenablediot
AT muazzamakhan adeeplearningbasedintrusiondetectionsystemformqttenablediot
AT sanaullahjan adeeplearningbasedintrusiondetectionsystemformqttenablediot
AT jawadahmad adeeplearningbasedintrusiondetectionsystemformqttenablediot
AT sajjadshaukatjamal adeeplearningbasedintrusiondetectionsystemformqttenablediot
AT awaisazizshah adeeplearningbasedintrusiondetectionsystemformqttenablediot
AT nikolaospitropakis adeeplearningbasedintrusiondetectionsystemformqttenablediot
AT williamjbuchanan adeeplearningbasedintrusiondetectionsystemformqttenablediot
AT muhammadalmaskhan deeplearningbasedintrusiondetectionsystemformqttenablediot
AT muazzamakhan deeplearningbasedintrusiondetectionsystemformqttenablediot
AT sanaullahjan deeplearningbasedintrusiondetectionsystemformqttenablediot
AT jawadahmad deeplearningbasedintrusiondetectionsystemformqttenablediot
AT sajjadshaukatjamal deeplearningbasedintrusiondetectionsystemformqttenablediot
AT awaisazizshah deeplearningbasedintrusiondetectionsystemformqttenablediot
AT nikolaospitropakis deeplearningbasedintrusiondetectionsystemformqttenablediot
AT williamjbuchanan deeplearningbasedintrusiondetectionsystemformqttenablediot
_version_ 1718431650949365760