{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T06:05:03Z","timestamp":1789538703155,"version":"build-2803163510"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T00:00:00Z","timestamp":1789516800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>The increasing utilization of the Message Queuing Telemetry Transport (MQTT) protocol in IoMT has created a high demand for efficient intrusion detection systems (IDSs).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study proposes a protocol-specific intrusion detection system (IDS) that employs a hybrid deep learning architecture consisting of a one-dimensional convolutional neural network along with a multi-head self-attention mechanism (CNN-MHSA). The architecture employs a convolutional feature-extraction module to derive local traffic features and a multi-head self-attention mechanism to capture long-range feature correlations. The proposed approach is evaluated on the CICIoMT2024 dataset, focusing mainly on the MQTT attack scenarios that are framed as a binary classification problem, in which five distinct MQTT attack variants (DoS-Connect Flood, DDoS-Connect Flood, DoS-Publish Flood, DDoS-Publish Flood, and Malformed Data) were consolidated into a single attack class against benign traffic.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The test results show an accuracy of 99.40%, an F1-score of 99.52%, and an AUC of 0.9998, respectively, for the proposed method.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The results indicate that the proposed CNN\u2013MHSA framework offers a robust benchmark for secure healthcare communication and can successfully identify MQTT threats in IoMT networks.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1934767","type":"journal-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:33:11Z","timestamp":1789536791000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Attention-enhanced deep learning model for MQTT intrusion detection in internet of medical things"],"prefix":"10.3389","volume":"9","author":[{"given":"Siddhartha","family":"Singhal","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kakelli Anil","family":"Kumar","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"6062","DOI":"10.1109\/JIOT.2025.3525494","article-title":"Transformer-based intrusion detection for IoT networks","volume":"12","author":"Akuthota","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"25993","DOI":"10.1109\/ACCESS.2024.3367113","article-title":"Protecting smart-home IoT devices from MQTT attacks: an empirical study of ML-based IDS","volume":"12","author":"Alasmari","year":"2024","journal-title":"IEEE Access."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"109809","DOI":"10.1016\/j.comnet.2023.109809","article-title":"DoS\/DDoS-MQTT-IoT: a dataset for evaluating intrusions in IoT networks using the MQTT protocol","volume":"231","author":"Alatram","year":"2023","journal-title":"Comput. Netw."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"13215","DOI":"10.1038\/s41598-025-98056-2","article-title":"Artificial intelligence-driven cybersecurity system for internet of things using self-attention deep learning and metaheuristic algorithms","volume":"15","author":"Alblehai","year":"2025","journal-title":"Sci. Rep."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1016\/j.aej.2023.01.060","article-title":"The internet of things healthcare monitoring system based on MQTT protocol","volume":"69","author":"Alshammari","year":"2023","journal-title":"Alex. Eng. J."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"45762","DOI":"10.1109\/ACCESS.2024.3380816","article-title":"A self-attention-based deep convolutional neural networks for IIoT networks intrusion detection","volume":"12","author":"Alshehri","year":"2024","journal-title":"IEEE Access."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"111897","DOI":"10.1016\/j.dib.2025.111897","article-title":"MQTTEEB-D: a real-world IoT cybersecurity dataset for AI-powered threat detection in MQTT networks","volume":"62","author":"Aqachtoul","year":"2025","journal-title":"Data Brief"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"105805","DOI":"10.1016\/j.engappai.2022.105805","article-title":"GAN-AE: an unsupervised intrusion detection system for MQTT networks","volume":"119","author":"Boppana","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"101351","DOI":"10.1016\/j.iot.2024.101351","article-title":"CICIoMT2024: a benchmark dataset for multi-protocol security assessment in IoMT","volume":"28","author":"Dadkhah","year":"2024","journal-title":"Internet Things"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"2059","DOI":"10.1007\/s11277-023-10983-8","article-title":"Design of intrusion detection system using GA and CNN for MQTT-based IoT networks","volume":"134","author":"Dandapat","year":"2024","journal-title":"Wirel. Pers. Commun."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"4951","DOI":"10.1109\/TNSM.2023.3260039","article-title":"Unsupervised GAN-based intrusion detection system using temporal convolutional networks and self-attention","volume":"20","author":"de Araujo-Filho","year":"2023","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"102398","DOI":"10.1016\/j.vlsi.2025.102398","article-title":"Network traffic inspection to enhance anomaly detection in the internet of things using attention-driven deep learning","volume":"103","author":"Hernandez-Jaimes","year":"2025","journal-title":"Integration"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"3368","DOI":"10.1080\/03772063.2021.1955228","article-title":"MQTT vulnerabilities, attack vectors and solutions in the internet of things (IoT)","volume":"69","author":"Hintaw","year":"2023","journal-title":"IETE J. Res."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"8467","DOI":"10.1007\/s40747-024-01460-0","article-title":"SAGB: self-attention with gate and BiGRU network for intrusion detection","volume":"10","author":"Hu","year":"2024","journal-title":"Complex Intell. Syst."},{"key":"ref15","first-page":"168","volume-title":"In 2024 19th Iranian Conference on Intelligent Systems (ICIS)","author":"Mohammadi","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1007\/s10791-026-10310-x","article-title":"Quantized autonomous edge intrusion detection system for adaptive feature aware internet of medical things networks","volume":"29","author":"Mondal","year":"2026","journal-title":"Discover Computing."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1007\/s41870-023-01591-8","article-title":"Evaluation of quality of service parameters for MQTT communication in IoT application by using deep neural network","volume":"16","author":"Pawar","year":"2024","journal-title":"Int. J. Inf. Technol."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1263","DOI":"10.1007\/s10207-022-00611-9","article-title":"An efficient intrusion detection system for MQTT-IoT using enhanced chaotic salp swarm algorithm and light GBM","volume":"21","author":"Prajisha","year":"2022","journal-title":"Int. J. Inf. Secur."},{"key":"ref19","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1016\/B978-0-443-40379-8.00014-4","volume-title":"Cognitive and Meta Learning Strategies in Biomedical Research and Healthcare","author":"Praveenkumar","year":"2026"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"7855","DOI":"10.1109\/OJCOMS.2025.3610132","article-title":"Enhancing MQTT intrusion detection in IoT using machine learning and feature engineering","volume":"6","author":"Putro","year":"2025","journal-title":"IEEE Open J. Commun. Soc."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"103526","DOI":"10.1016\/j.cose.2023.103526","article-title":"Multi head self-attention gated graph convolutional network based multi attack intrusion detection in MANET","volume":"136","author":"Reka","year":"2024","journal-title":"Comput. Secur."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"415","DOI":"10.3390\/drones7070415","article-title":"A UAV-assisted Stackelberg game model for securing IoMT healthcare networks","volume":"7","author":"Shaikh","year":"2023","journal-title":"Drones."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1524286","DOI":"10.3389\/fmed.2025.1524286","article-title":"A deep reinforcement learning-based robust intrusion detection system for securing IoMT healthcare networks","volume":"12","author":"Shaikh","year":"","journal-title":"Front. Med."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1467241","DOI":"10.3389\/fdgth.2024.1467241","article-title":"RCLNet: an effective anomaly-based intrusion detection for securing the IoMT system","volume":"6","author":"Shaikh","year":"","journal-title":"Front. Digit. Health."},{"key":"ref25","volume-title":"Proc. 18th International Conference on Open Source Systems and Technologies (ICOSST)","author":"Shaikh","year":""},{"key":"ref26","doi-asserted-by":"publisher","first-page":"101597","DOI":"10.1016\/j.iot.2025.101597","article-title":"Memory feedback transformer based intrusion detection system for IoMT healthcare networks","volume":"32","author":"Shaikh","year":"","journal-title":"Internet Things"},{"key":"ref27","first-page":"123","volume-title":"Integrating Cloud, Fog, and Edge Computing in Healthcare: Federated Learning and Blockchain Approaches","author":"Sharma","year":"2026"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"33095","DOI":"10.1109\/ACCESS.2022.3161566","article-title":"Senmqtt-set: an intelligent intrusion detection in IoT-MQTT networks using ensemble multi cascade features","volume":"10","author":"Siddharthan","year":"2022","journal-title":"IEEE Access"},{"key":"ref29","first-page":"1","volume-title":"2024 4th International Conference on Digital Futures and Transformative Technologies (ICoDT2)","author":"Sohail","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1007\/s10472-025-09993-7","article-title":"A novel intrusion detection framework using ensemble learning in MQTT IoT applications","author":"Solanki","year":"2025","journal-title":"Ann. Math. Artif. Intell."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"110072","DOI":"10.1016\/j.comnet.2023.110072","article-title":"TNN-IDS: transformer neural network-based intrusion detection system for MQTT-enabled IoT networks","volume":"237","author":"Ullah","year":"","journal-title":"Comput. Netw."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"114590","DOI":"10.1109\/ACCESS.2023.3324657","article-title":"MAGRU-IDS: a multi-head attention-based gated recurrent unit for intrusion detection in IIoT networks","volume":"11","author":"Ullah","year":"","journal-title":"IEEE Access"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1016\/j.dcan.2023.07.011","article-title":"IDS-INT: intrusion detection system using transformer-based transfer learning for imbalanced network traffic","volume":"10","author":"Ullah","year":"2024","journal-title":"Digit Commun Netw"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"28718","DOI":"10.1038\/s41598-025-11348-5","article-title":"Network intrusion detection model using wrapper based feature selection and multi head attention transformers","volume":"15","author":"Umer","year":"2025","journal-title":"Sci. Rep."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"e409","DOI":"10.1002\/spy2.409","article-title":"Security and privacy challenges, issues, and enhancing techniques for internet of medical things: a systematic review","volume":"7","author":"Wani","year":"2024","journal-title":"Secur. Priv."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"1075","DOI":"10.1007\/s10207-023-00699-3","article-title":"Securing MQTT protocol for IoT environment using IDS based on ensemble learning","volume":"22","author":"Zeghida","year":"2023","journal-title":"Int. J. Inf. Secur."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1007\/s10586-024-04752-5","article-title":"Enhancing IoT cyber attacks intrusion detection through GAN-based data augmentation and hybrid deep learning models for MQTT network protocol cyber attacks","volume":"28","author":"Zeghida","year":"","journal-title":"Clust. Comput."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1007\/s10207-025-01036-w","article-title":"XMID-MQTT: explaining machine learning-based intrusion detection system for MQTT protocol in IoT environment","volume":"24","author":"Zeghida","year":"","journal-title":"Int. J. Inf. Secur."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"25700","DOI":"10.1109\/ACCESS.2024.3363889","article-title":"Realtime feature engineering for anomaly detection in IoT based MQTT networks","volume":"12","author":"Zuhairi","year":"2024","journal-title":"IEEE Access."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1934767\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:33:12Z","timestamp":1789536792000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1934767\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,16]]},"references-count":39,"alternative-id":["10.3389\/frai.2026.1934767"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1934767","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,16]]},"article-number":"1934767"}}