Hybrid Deep Learning Based Intrusion Detection System for Rpl Iot Network

38 Pages Posted: 27 Dec 2021

See all articles by Yahya Al Sawafi

Yahya Al Sawafi

Sultan Qaboos University

Abderezak Touzene

Sultan Qaboos University

Rachid Hedjam

Sultan Qaboos University

Abstract

Internet of things (IoT) has become an emerging technology transforming everyday physical objects to be smarter by using underlying technologies such as sensor networks. Routing protocol for low power and lossy network (RPL) is considered one of the promising protocols designed for IoT networks. However, due to the constrained nature of the IoT devices in terms of memory, processing power, and network capabilities, they are exposed to many security attacks. Unfortunately, the existing Intrusion Detection System (IDS) approaches using machine learning that has been proposed to detect and mitigate security attacks in internet networks are not suitable for analyzing IoT traffics. This paper proposed an IDS system using the hybridization of supervised and semi-supervised deep learning for network traffic classification of known and unknown abnormal behaviors in the IoT environment. In addition, we have developed a new IoT specialized dataset named IoTR-DS, using the RPL protocol. IoTR-DS is used as a use case to classify three known security attacks (DIS, Rank, and Wormhole). The proposed Hybrid DL-Based IDS is evaluated and compared to some existing ones, and the results are promising. The evaluation results show an accuracy-detecting rate of 98% and 93% f1-score of multi-class attacks when using pre-trained attacks (known) and an average accuracy of 95% and 87% f1-score when predicting untrained two attack behaviors (unknown).

Keywords: Intrusion Detection Systems, Deep Learning, Machine Learning, security, RPL, Routing protocols.

Suggested Citation

Al Sawafi, Yahya and Touzene, Abderezak and Hedjam, Rachid, Hybrid Deep Learning Based Intrusion Detection System for Rpl Iot Network. Available at SSRN: https://ssrn.com/abstract=3994183 or http://dx.doi.org/10.2139/ssrn.3994183

Yahya Al Sawafi (Contact Author)

Sultan Qaboos University ( email )

PO Box 20
Al-khod SQU 123
Muscat
Oman

Abderezak Touzene

Sultan Qaboos University ( email )

PO Box 20
Al-khod SQU 123
Muscat
Oman

Rachid Hedjam

Sultan Qaboos University ( email )

PO Box 20
Al-khod SQU 123
Muscat
Oman

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
119
Abstract Views
509
Rank
481,386
PlumX Metrics