Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Detecting anomalies in MQTT/MQTT-SN traffic using intelligent learning models

Bulletin of Electrical Engineering and Informatics · Vol. 15 No. 3 (2026) · hlm. 2747–2757

DOI
10.11591/eei.v15i3.11889
ISSN
2089-3191, 2302-9285
Terbit
2026-06-01
Penerbit
Institute of Advanced Engineering and Science (IAES)
Bahasa
en
Lisensi
creativecommons.org/licenses/by-sa/4.0/

Abstrak

The widespread adoption of the internet of things (IoT) has heightened demand for secure, efficient communication across constrained devices. Lightweight protocols such as message queuing telemetry transport (MQTT) and its variant MQTT-sensor networks (SN) are widely used for IoT messaging but lack intrinsic security mechanisms, leaving them vulnerable to denial-of-service, spoofing, and injection attacks. This study presents a machine learning (ML)-based anomaly detection framework designed to enhance the security of MQTT and MQTT-SN traffic. We emulate realistic IoT environments to generate both benign and malicious traffic, extracting protocol-specific features such as packet length, topic length, quality of service (QoS) levels, and publish frequency. Three supervised models—random forest (RF), eXtreme gradient boosting (XGBoost), and long short-term memory (LSTM)—were trained and evaluated using cross-validation and statistical performance metrics. Experimental findings demonstrate that XGBoost achieved the best overall results, with 97.4% accuracy, 95.9% F1-score, and low false-positive and false-negative rates. Furthermore, the framework was successfully deployed on edge devices such as Raspberry Pi Zero W and ESP32, confirming its real-time feasibility and efficiency. The proposed approach highlights the potential of intelligent learning models to deliver lightweight, deployable, and effective intrusion detection for IoT systems utilizing MQTT and MQTT-SN communication protocols.

Kata kunci

Jaringan kolaborasi para penulis

40 penulis · 98 tautan kepenulisan bersama · 55 lintas organisasi · menampilkan 40 yang paling banyak terhubung

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Universiti Sains Malaysia
  • Universiti of Malaysia Sabah
  • Al-Ahliyya Amman University
  • Universiti Malaysia Perlis
  • Princess Sumaya University for Technology
  • Liwa University
  • Southern Technical University
  • Organisasi lain
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
‪Mahmood A. Al-Shareeda‬Southern Technical University6
Mosleh M. AbualhajAl-Ahliyya Amman University5
Shankar KaruppayahUniversiti Sains Malaysia4
Iznan Husainy HasbullahUniversiti Sains Malaysia4
Sumaya Nabil Al-KhatibAl-Ahliyya Amman University3
Hamzah Hadi QasimIraq University College3
Abeer Abdullah AlsadhanImam Abdulrahman Bin Faisal University3
Rosni AbdullahUniversiti Sains Malaysia3
Alhamza AlalousiUniversiti Malaysia Perlis2
Rozmie Razif OthmanUniversiti Malaysia Perlis2
Shahrul NizamUniversiti Malaysia Perlis2
Anwar H. KatrawiUniversiti Sains Malaysia2
Ammar Kamal AbasiUniversiti Sains Malaysia2
Riyadh Rahef NuiaaUniversiti Sains Malaysia2
Ali Hakem AlsaeediUniversity of Al-Qadisiyah2
Yu‐Beng LeauUniversiti of Malaysia Sabah2
Anas Abu TalebPrincess Sumaya University for Technology2
Ismail Mohamed KeshtaAlmaarefa University2
Devamekalai NagasundaramUniversiti Sains Malaysia2
Huda Mohammed AlsayednoorShatt Al-Arab University College2
Mohammad O. HiariAl-Ahliyya Amman University2
Shams Ul Arfeen LaghariBahrain Polytechnic2
Ibrahim AlShourbajiAfiliasi tidak diketahui1
Zaid Abdi Alkareem AlyasseriUniversity of Kufa1
Adnan Hasan Bdair AIghuraibawiUniversiti Sains Malaysia1
Esraa Saleh AlomariUniversity of Wasit1
Low Xian WeeUniversiti of Malaysia Sabah1
Zhiwei YanChina Internet Network Information Center1
Yong Jin ParkUniversiti of Malaysia Sabah1
Qasem S. Abu Al-HaijaJordan University of Science and Technology1
Arkan Hammoodi Hasan KablaUniversiti Sains Malaysia1
Shady HamoudaLiwa University1
Abdullah Ahmed BahashwanUniversiti Sains Malaysia1
Taief Alaa Al-AmiedyUniversiti Sains Malaysia1
Serri FaisalLiwa University1
Mohammad Shahrul Mohd ShahUniversiti of Malaysia Sabah1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OpenAlex API (jurnal SINTA, ADR 0048) https://openalex.org/S2765016208, pertama di-harvest 19 Nov 2026, terakhir terlihat 19 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"><dc:title xml:lang="en">Detecting anomalies in MQTT/MQTT-SN traffic using intelligent learning models</dc:title><dc:creator>Nabeel Alassaf</dc:creator><dc:creator>Selvakumar Manickam</dc:creator><dc:creator>Ammar Odeh</dc:creator><dc:creator>Mohammed Anbar</dc:creator><dc:subject>MQTT</dc:subject><dc:subject>MQTT-SN</dc:subject><dc:subject>anomaly detection</dc:subject><dc:subject>intrusion detection</dc:subject><dc:subject>Internet of Things security</dc:subject><dc:subject>lightweight protocols</dc:subject><dc:subject>denial-of-service attacks</dc:subject><dc:subject>spoofing attacks</dc:subject><dc:subject>injection attacks</dc:subject><dc:subject>XGBoost</dc:subject><dc:subject>random forest</dc:subject><dc:subject>LSTM</dc:subject><dc:subject>edge deployment</dc:subject><dc:subject>real-time detection</dc:subject><dc:subject>resource-constrained devices</dc:subject><dc:description xml:lang="en">The widespread adoption of the internet of things (IoT) has heightened demand for secure, efficient communication across constrained devices. Lightweight protocols such as message queuing telemetry transport (MQTT) and its variant MQTT-sensor networks (SN) are widely used for IoT messaging but lack intrinsic security mechanisms, leaving them vulnerable to denial-of-service, spoofing, and injection attacks. This study presents a machine learning (ML)-based anomaly detection framework designed to enhance the security of MQTT and MQTT-SN traffic. We emulate realistic IoT environments to generate both benign and malicious traffic, extracting protocol-specific features such as packet length, topic length, quality of service (QoS) levels, and publish frequency. Three supervised models—random forest (RF), eXtreme gradient boosting (XGBoost), and long short-term memory (LSTM)—were trained and evaluated using cross-validation and statistical performance metrics. Experimental findings demonstrate that XGBoost achieved the best overall results, with 97.4% accuracy, 95.9% F1-score, and low false-positive and false-negative rates. Furthermore, the framework was successfully deployed on edge devices such as Raspberry Pi Zero W and ESP32, confirming its real-time feasibility and efficiency. The proposed approach highlights the potential of intelligent learning models to deliver lightweight, deployable, and effective intrusion detection for IoT systems utilizing MQTT and MQTT-SN communication protocols.</dc:description><dc:publisher>Institute of Advanced Engineering and Science (IAES)</dc:publisher><dc:date>2026-06-01</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:format>application/pdf</dc:format><dc:identifier>https://doi.org/10.11591/eei.v15i3.11889</dc:identifier><dc:identifier>10.11591/eei.v15i3.11889</dc:identifier><dc:source>Bulletin of Electrical Engineering and Informatics; Vol 15 No 3 (2026); 2747-2757</dc:source><dc:source>2089-3191</dc:source><dc:source>2302-9285</dc:source><dc:language>en</dc:language><dc:relation>https://beei.org/index.php/EEI/article/download/11889/4811</dc:relation><dc:rights>https://creativecommons.org/licenses/by-sa/4.0/</dc:rights></oai_dc:dc>