A Cost-Sensitive Machine Learning Model With Multitask Learning for Intrusion Detection in IoT

Journal article (2023)

Authors

Akbar Telikani University of Wollongong
Nima Esmi Rudbardeh Rijksuniversiteit Groningen
Shiva Soleymanpour University of Guilan
Asadollah Shahbahrami University of Guilan
Jun Shen University of Wollongong
G. Gaydadjiev Rijksuniversiteit Groningen
Reza Hassanpour Erasmus Universiteit Rotterdam, Gidatarim University Konya-Turkey
Research Group
Quantum Circuit Architectures and Technology (EEMCS) (TU Delft)
Internet of Things Intrusion detection Deep learning (DL) Training Costs Task analysis Support vector machines Mathematical models Support vector machine (SVM) Intrusion detection Multitask learning Internet of things (IoT)
More Info
expand_more

Published Date

2023

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Department

Quantum & Computer Engineering

Research Group

Quantum Circuit Architectures and Technology

Abstract

A problem with machine learning (ML) techniques for detecting intrusions in the Internet of Things (IoT) is that they are ineffective in the detection of low-frequency intrusions. In addition, as ML models are trained using specific attack categories, they cannot recognize unknown attacks. This article integrates strategies of cost-sensitive learning and multitask learning into a hybrid ML model to address these two challenges. The hybrid model consists of an autoencoder for feature extraction and a support vector machine (SVM) for detecting intrusions. In the cost-sensitive learning phase for the class imbalance problem, the hinge loss layer is enhanced to make a classifier strong against low-distributed intrusions. Moreover, to detect unknown attacks, we formulate the SVM as a multitask problem. Experiments on the UNSW-NB15 and BoT-IoT datasets demonstrate the superiority of our model in terms of recall, precision, and F1-score averagely 92.2%, 96.2%, and 94.3%, respectively, over other approaches.