Machine Learning-Enhanced Attribute-Based Authentication for Secure IoT Access Control

The rapid growth of Internet of Things (IoT) devices across industrial and critical sectors requires robust and efficient authentication mechanisms. Traditional authentication systems struggle to balance security, privacy and computational efficiency, particularly in resource-constrained environment...

Full description

Saved in:
Bibliographic Details
Main Authors: Jibran Saleem, Umar Raza, Mohammad Hammoudeh, William Holderbaum
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/9/2779
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849312894736400384
author Jibran Saleem
Umar Raza
Mohammad Hammoudeh
William Holderbaum
author_facet Jibran Saleem
Umar Raza
Mohammad Hammoudeh
William Holderbaum
author_sort Jibran Saleem
collection DOAJ
description The rapid growth of Internet of Things (IoT) devices across industrial and critical sectors requires robust and efficient authentication mechanisms. Traditional authentication systems struggle to balance security, privacy and computational efficiency, particularly in resource-constrained environments such as Industry 4.0. This research presents the SmartIoT Hybrid Machine Learning (ML) Model, a novel integration of Attribute-Based Authentication and a lightweight machine learning algorithm designed to enhance security while minimising computational overhead. The SmartIoT Hybrid ML Model utilises Random Forest classifiers for real-time anomaly detection, dynamically assessing access requests based on user attributes, login patterns and behavioural analysis. The model enhances identity protection while enabling secure authentication without exposing sensitive information by incorporating privacy-preserving Attribute-Based Credentials and Attribute-Based Signatures. Our experimental evaluation demonstrates 86% authentication accuracy, 88% precision and 96% recall, significantly outperforming existing solutions while maintaining an average response time of 112ms, making it suitable for low-power IoT devices. Comparative analysis with state-of-the-art authentication frameworks shows the model’s security resilience, computational efficiency and adaptability in real-world IoT applications.
format Article
id doaj-art-86128dcb5c0e407c9fd6c1111089bfc6
institution Kabale University
issn 1424-8220
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-86128dcb5c0e407c9fd6c1111089bfc62025-08-20T03:52:56ZengMDPI AGSensors1424-82202025-04-01259277910.3390/s25092779Machine Learning-Enhanced Attribute-Based Authentication for Secure IoT Access ControlJibran Saleem0Umar Raza1Mohammad Hammoudeh2William Holderbaum3Department of Engineering, Faculty of Science and Engineering, Manchester Metropolitan University, Manchester M1 5GD, UKDepartment of Engineering, Faculty of Science and Engineering, Manchester Metropolitan University, Manchester M1 5GD, UKDepartment of Computing and Mathematics, Faculty of Science and Engineering, Manchester Metropolitan University, Manchester M1 5GD, UKDepartment of Engineering, Faculty of Science and Engineering, Manchester Metropolitan University, Manchester M1 5GD, UKThe rapid growth of Internet of Things (IoT) devices across industrial and critical sectors requires robust and efficient authentication mechanisms. Traditional authentication systems struggle to balance security, privacy and computational efficiency, particularly in resource-constrained environments such as Industry 4.0. This research presents the SmartIoT Hybrid Machine Learning (ML) Model, a novel integration of Attribute-Based Authentication and a lightweight machine learning algorithm designed to enhance security while minimising computational overhead. The SmartIoT Hybrid ML Model utilises Random Forest classifiers for real-time anomaly detection, dynamically assessing access requests based on user attributes, login patterns and behavioural analysis. The model enhances identity protection while enabling secure authentication without exposing sensitive information by incorporating privacy-preserving Attribute-Based Credentials and Attribute-Based Signatures. Our experimental evaluation demonstrates 86% authentication accuracy, 88% precision and 96% recall, significantly outperforming existing solutions while maintaining an average response time of 112ms, making it suitable for low-power IoT devices. Comparative analysis with state-of-the-art authentication frameworks shows the model’s security resilience, computational efficiency and adaptability in real-world IoT applications.https://www.mdpi.com/1424-8220/25/9/2779attribute-based authenticationmachine learninghybrid MLIoTrandom forestsecurity
spellingShingle Jibran Saleem
Umar Raza
Mohammad Hammoudeh
William Holderbaum
Machine Learning-Enhanced Attribute-Based Authentication for Secure IoT Access Control
Sensors
attribute-based authentication
machine learning
hybrid ML
IoT
random forest
security
title Machine Learning-Enhanced Attribute-Based Authentication for Secure IoT Access Control
title_full Machine Learning-Enhanced Attribute-Based Authentication for Secure IoT Access Control
title_fullStr Machine Learning-Enhanced Attribute-Based Authentication for Secure IoT Access Control
title_full_unstemmed Machine Learning-Enhanced Attribute-Based Authentication for Secure IoT Access Control
title_short Machine Learning-Enhanced Attribute-Based Authentication for Secure IoT Access Control
title_sort machine learning enhanced attribute based authentication for secure iot access control
topic attribute-based authentication
machine learning
hybrid ML
IoT
random forest
security
url https://www.mdpi.com/1424-8220/25/9/2779
work_keys_str_mv AT jibransaleem machinelearningenhancedattributebasedauthenticationforsecureiotaccesscontrol
AT umarraza machinelearningenhancedattributebasedauthenticationforsecureiotaccesscontrol
AT mohammadhammoudeh machinelearningenhancedattributebasedauthenticationforsecureiotaccesscontrol
AT williamholderbaum machinelearningenhancedattributebasedauthenticationforsecureiotaccesscontrol