• Home
  • Search
  • Securing a Smart Home with a Transformer-Based IoT Intrusion Detection System
  • Cite Icon74
  • https://doi.org/10.3390/electronics12092100Copy DOI Icon

Securing a Smart Home with a Transformer-Based IoT Intrusion Detection System

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Machine learning (ML)-based Network Intrusion Detection Systems (NIDSs) can classify each network’s flow behavior as benign or malicious by detecting heterogeneous features, including both categorical and numerical features. However, the present ML-based NIDSs are deemed insufficient in terms of their ability to generalize, particularly in changing network environments such as the Internet of Things (IoT)-based smart home. Although IoT devices add so much to home comforts, they also introduce potential risks and vulnerabilities. Recently, many NIDS studies on other IoT scenarios, such as the Internet of Vehicles (IoV) and smart cities, focus on utilizing the telemetry data of IoT devices for IoT intrusion detection. Because when IoT devices are under attack, their abnormal telemetry data values can reflect the anomaly state of those devices. Those telemetry data-based IoT NIDS methods detect intrusion events from a different view, focusing on the attack impact, from the traditional network traffic-based NIDS, which focuses on analyzing attack behavior. The telemetry data-based NIDS is more suitable for IoT devices without built-in security mechanisms. Considering the smart home IoT scenario, which has a smaller scope and a limited number of IoT devices compared to other IoT scenarios, both NIDS views can work independently. This motivated us to propose a novel ML-based NIDS to combine the network traffic-based and telemetry data-based NIDS together. In this paper, we propose a Transformer-based IoT NIDS method to learn the behaviors and effects of attacks from different types of data that are generated in the heterogeneous IoT environment. The proposed method utilizes a self-attention mechanism to learn contextual embeddings for input network features. Based on the contextual embeddings, our method can solve the feature set challenge, including both continuous and categorical features. Our method is the first to utilize both network traffic data and IoT sensors’ telemetry data at the same time for intrusion detection. Experiments reveal the effectiveness of our method on a realistic network traffic intrusion detection dataset named ToN_IoT, with an accuracy of 97.95% for binary classification and 95.78% for multiple classifications on pure network data. With the extra IoT information, the performance of our method has been improved to 98.39% and 97.06%, respectively. A comparative study with existing works shows that our method can achieve state-of-the-art performance on the ToN_IoT dataset.

Loading PDF

Similar Papers
  • Research Article

IPASecIoT: An Intelligent Pipeline for Automatic and Adaptive Feature Extraction for Secure IoT Device Identification and Intrusion Detection

  • Oct 01, 2025
  • Internet of Things
  • Ogobuchi Daniel Okey +4
  • PDF
  • Research Article
  • Citations33

Resistance of IoT Sensors against DDoS Attack in Smart Home Environment

  • Sep 16, 2020
  • Sensors (Basel, Switzerland)
  • Ladislav Huraj +2
  • Research Article
  • Citations22

A Novel Lightweight IoT Intrusion Detection Model Based on Self-Knowledge Distillation

  • Jun 01, 2025
  • IEEE Internet of Things Journal
  • Zhendong Wang +4
  • Research Article
  • Citations39

A Lightweight and Efficient IoT Intrusion Detection Method Based on Feature Grouping

  • Jan 15, 2024
  • IEEE Internet of Things Journal
  • Mingshu He +4
  • Research Article
  • Citations201

A Survey on IoT Intrusion Detection: Federated Learning, Game Theory, Social Psychology, and Explainable AI as Future Directions

  • Mar 01, 2023
  • IEEE Internet of Things Journal
  • Sarhad Arisdakessian +4
  • Conference Article
  • Citations5

Performance Analysis of Deep Learning Algorithms for Intrusion Detection in IoT

  • Jun 16, 2021
  • Jinsi Jose +1
  • Supplementary Content
  • Citations159

Intrusion Detection in Internet of Things Systems: A Review on Design Approaches Leveraging Multi-Access Edge Computing, Machine Learning, and Datasets

  • May 14, 2022
  • Sensors (Basel, Switzerland)
  • Eric Gyamfi +1
  • Conference Article
  • Citations25

Enhanced network intrusion detection system protocol for internet of things

  • Mar 30, 2020
  • Bacem Mbarek +2
  • Conference Article
  • Citations3

GaaS: Adaptive Cross-Platform Gateway for IoT Applications

  • Nov 01, 2019
  • Mohamed Abdelaal +4
  • Research Article
  • Citations68

Enhancing intrusion detection in IoT networks using machine learning-based feature selection and ensemble models

  • Mar 02, 2024
  • Systems Science & Control Engineering
  • Ayoob Almotairi +3
  • Conference Article
  • Citations11

Network Intrusion Detection System in a Light Bulb

  • Nov 30, 2022
  • Liam Daly Manocchio +2
  • Conference Article
  • Citations3

An End-to-End System for Monitoring IoT Devices in Smart Homes

  • Jan 08, 2022
  • Keith Erkert +6
  • PDF
  • Conference Article
  • Citations16

Machine Learning for Intrusion Detection: Stream Classification Guided by Clustering for Sustainable Security in IoT

  • Jun 05, 2023
  • Martin Manuel Lopez +3
  • Research Article
  • Citations234

Evaluating Federated Learning for intrusion detection in Internet of Things: Review and challenges

  • Dec 14, 2021
  • Computer Networks
  • Enrique Mármol Campos +6
  • Conference Article
  • Citations3

Internet of Things Intrusion Detection System based on Transfer Learning

  • May 27, 2022
  • Wang Yutao +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.