Institutul de Matematică şi Informatică "Vladimir Andrunachievici"
Universitatea de Stat din MoldovaRO EN
An Intelligent Detection of Malicious Intrusions in IoT Based on Machine Learning and Deep Learning Techniques
Authors: Saman Iftikhar, Danish Khan, Daniah Al-Madani, Khattab M. Ali Alheeti, Kiran Fatima
– 0.39 Mb
Abstract
The devices of the Internet of Things (IoT) are facing various types of attacks, and IoT applications present unique and new protection challenges. These security challenges in IoT must be addressed to avoid any potential attacks. Malicious intrusions in IoT devices are considered one of the most aspects required for IoT users in modern applications. Machine learning techniques are widely used for intelligent detection of malicious intrusions in IoT. This paper proposes an intelligent detection method of malicious intrusions in IoT systems that leverages effective classification of benign and malicious attacks. An ensemble approach combined with various machine learning algorithms and a deep learning technique, is used to detect anomalies and other malicious activities in IoT. For the consideration of the detection of malicious intrusions and anomalies in IoT devices, UNSW-NB15 dataset is used as one of the latest IoT datasets. In this research, malicious and normal intrusions in IoT devices are classified with the use of various models. %Moreover, improved results are provided and compared with CorrAuc [1] for training accuracies, cross-validation accuracies, execution time, precision, recall and F1 score.Saman Iftikhar
Faculty of Computer Studies, Arab Open University, Saudi Arabia
E-mail:
Danish Khan
Department of Computer Science, COMSATS University Islamabad
Wah Campus, Wah Cantt Pakistan
E-mail:
Daniah Al-Madani
Faculty of Computer Studies, Arab Open University, Saudi Arabia
E-mail:
Khattab M Ali Alheeti
Computer Networking Systems Department,
College of Computer Sciences and Information Technology,
University of Anbar, Anbar, Iraq
E-mail:
Kiran Fatimah
TAFE, NSW Australia
E-mail:
Faculty of Computer Studies, Arab Open University, Saudi Arabia
E-mail:
Danish Khan
Department of Computer Science, COMSATS University Islamabad
Wah Campus, Wah Cantt Pakistan
E-mail:
Daniah Al-Madani
Faculty of Computer Studies, Arab Open University, Saudi Arabia
E-mail:
Khattab M Ali Alheeti
Computer Networking Systems Department,
College of Computer Sciences and Information Technology,
University of Anbar, Anbar, Iraq
E-mail:
Kiran Fatimah
TAFE, NSW Australia
E-mail:
DOI
https://doi.org/10.56415/csjm.v30.16Fulltext
– 0.39 Mb
Contents
- Foreword
- An Intelligent Detection of Malicious Intrusions in IoT Based on Machine Learning and Deep Learning Techniques
- Residual Neural Network in Genomics
- Privacy and Reader-first Authentication in Vaudenay's RFID Model with Temporary State Disclosure
- Kurtosis-Based Feature Selection Method using Symmetric Uncertainty to Predict the Air Quality Index
- Wiener Index of Some Brooms
- Graph-based decision making for varying complexity multicriteria problems
