IoT Malware Detection Based on OPCODE Purification

Ibrahim Gülataş; Haci Hakan Kilinç; Muhammed Ali Aydin; Abdul Halim Zaim

doi:10.5152/electrica.2023.23043

IoT Malware Detection Based on OPCODE Purification

Ibrahim Gülataş^*, Haci Hakan Kilinç, Muhammed Ali Aydin, Abdul Halim Zaim

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

Malware threat for Internet of Things (IoT) devices is increasing day by day. The constrained nature of IoT devices makes it impossible to apply high- resou rce-d emand ing anti-malware tools for these devices. Therefore there is an enormous need for lightweight and efficient anti-malware solutions for IoT devices. In this study, machine learning-based malware detection is performed using purified OPCODE analysis for IoT devices with MIPS architecture. The proposed methodology reduced the runtime of IoT malware detection up to 7.2 times without reducing the accuracy ratio.

Original language	English
Pages (from-to)	634-642
Number of pages	9
Journal	Electrica
Volume	23
Issue number	3
DOIs	https://doi.org/10.5152/electrica.2023.23043
Publication status	Published - Sept 2023
Externally published	Yes

Bibliographical note

Publisher Copyright:
© 2023 Istanbul University. All rights reserved.

Keywords

Internet of Things Malware detection
Operation Code analysis
malware analysis

Access to Document

10.5152/electrica.2023.23043

Cite this

@article{2692d0a36562454081bb19d88f388ec8,

title = "IoT Malware Detection Based on OPCODE Purification",

abstract = "Malware threat for Internet of Things (IoT) devices is increasing day by day. The constrained nature of IoT devices makes it impossible to apply high- resou rce-d emand ing anti-malware tools for these devices. Therefore there is an enormous need for lightweight and efficient anti-malware solutions for IoT devices. In this study, machine learning-based malware detection is performed using purified OPCODE analysis for IoT devices with MIPS architecture. The proposed methodology reduced the runtime of IoT malware detection up to 7.2 times without reducing the accuracy ratio.",

keywords = "Internet of Things Malware detection, Operation Code analysis, malware analysis",

author = "Ibrahim G{\"u}lata{\c s} and Kilin{\c c}, {Haci Hakan} and Aydin, {Muhammed Ali} and Zaim, {Abdul Halim}",

year = "2023",

month = sep,

doi = "10.5152/electrica.2023.23043",

language = "English",

volume = "23",

pages = "634--642",

journal = "Electrica",

issn = "1303-0914",

publisher = "Istanbul University",

number = "3",

}

TY - JOUR

T1 - IoT Malware Detection Based on OPCODE Purification

AU - Gülataş, Ibrahim

AU - Kilinç, Haci Hakan

AU - Aydin, Muhammed Ali

AU - Zaim, Abdul Halim

PY - 2023/9

Y1 - 2023/9

N2 - Malware threat for Internet of Things (IoT) devices is increasing day by day. The constrained nature of IoT devices makes it impossible to apply high- resou rce-d emand ing anti-malware tools for these devices. Therefore there is an enormous need for lightweight and efficient anti-malware solutions for IoT devices. In this study, machine learning-based malware detection is performed using purified OPCODE analysis for IoT devices with MIPS architecture. The proposed methodology reduced the runtime of IoT malware detection up to 7.2 times without reducing the accuracy ratio.

AB - Malware threat for Internet of Things (IoT) devices is increasing day by day. The constrained nature of IoT devices makes it impossible to apply high- resou rce-d emand ing anti-malware tools for these devices. Therefore there is an enormous need for lightweight and efficient anti-malware solutions for IoT devices. In this study, machine learning-based malware detection is performed using purified OPCODE analysis for IoT devices with MIPS architecture. The proposed methodology reduced the runtime of IoT malware detection up to 7.2 times without reducing the accuracy ratio.

KW - Internet of Things Malware detection

KW - Operation Code analysis

KW - malware analysis

UR - http://www.scopus.com/inward/record.url?scp=85215395355&partnerID=8YFLogxK

U2 - 10.5152/electrica.2023.23043

DO - 10.5152/electrica.2023.23043

M3 - Article

AN - SCOPUS:85215395355

SN - 1303-0914

VL - 23

SP - 634

EP - 642

JO - Electrica

JF - Electrica

IS - 3

ER -

IoT Malware Detection Based on OPCODE Purification

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this