Intelligent Deep Learning for Anomaly-Based Intrusion Detection in IoT Smart Home Networks

Nazia Butt, Ana Shahid, Kashif Naseer Qureshi, Sajjad Haider, Ashraf Osman Ibrahim, Faisal Binzagr, Noman Arshad

Research output: Contribution to journalArticlepeer-review

Abstract

The Internet of Things (IoT) is a tremendous network based on connected smart devices. These networks sense and transmit data by using advanced communication standards and technologies. The smart home is one of the areas of IoT networks, where home appliances are connected to the internet and smart grids. However, these networks are at high risk in terms of security violations. Different kinds of attacks have been conducted on these networks where the user lost their data. Intrusion detection systems (IDSs) are used to detect and prevent cyberattacks. These systems are based on machine and deep learning techniques and still suffer from fitting or overfitting issues. This paper proposes a novel solution for anomaly-based intrusion detection for smart home networks. The proposed model addresses overfitting/underfitting issues and ensures high performance in terms of hybridization. The proposed solution uses feature selection and hyperparameter tuning and was tested with an existing dataset. The experimental results indicated a significant increase in performance while minimizing misclassification and other limitations as compared to state-of-the-art solutions.

Original languageEnglish
Article number4598
JournalMathematics
Volume10
Issue number23
DOIs
Publication statusPublished - Dec 2022

Keywords

  • attacks
  • detection
  • internet of things
  • intrusion
  • machine learning
  • smart homes

Fingerprint

Dive into the research topics of 'Intelligent Deep Learning for Anomaly-Based Intrusion Detection in IoT Smart Home Networks'. Together they form a unique fingerprint.

Cite this