Binary and multiclass malware classification of windows portable executable using classic machine learning and deep learning

Cybersecurity has become a significant concern in recent decades. Enhancing cybersecurity and safeguarding important information systems are essential in today’s world. It is now one of the most important challenges in the realm of IT. Malware has become a significant issue in the modern digital age...

Full description

Saved in:
Bibliographic Details
Main Authors: Moeiz Miraoui, Mohamed Ben Belgacem
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-03-01
Series:Frontiers in Computer Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fcomp.2025.1539519/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849773332018233344
author Moeiz Miraoui
Mohamed Ben Belgacem
author_facet Moeiz Miraoui
Mohamed Ben Belgacem
author_sort Moeiz Miraoui
collection DOAJ
description Cybersecurity has become a significant concern in recent decades. Enhancing cybersecurity and safeguarding important information systems are essential in today’s world. It is now one of the most important challenges in the realm of IT. Malware has become a significant issue in the modern digital age. The primary objectives of malware are to disrupt, harm, or impair computer systems and information systems without the user’s consent or awareness. Currently, malwares are viewed as some of the most prevalent cyber threats. The prevalence of Windows operating system has made it a prime target for malware attacks. PE (Portable Executable) is the standard file format for executable files and DLLs on Windows systems, with PE malware being the most common form of malicious software. Static analysis, which is mainly a signature-based method for detecting malware, can only identify already known malware. The main weakness of this approach is its struggle with obfuscation, such as encryption and packing. The use of machine learning methods has demonstrated significant potential in the field of malware detection and is an emerging field with many opportunities. Most previous works focus on binary classification, limited number of ML algorithms and even a single dataset. In this paper, we present both a binary and multiclass PE malware classification using four classic machine learning algorithms and four deep learning algorithms. We have applied this algorithm on three publicly available datasets and deduced the best algorithm depending on the number of features and dataset size.
format Article
id doaj-art-1617bfdad0b34cf2a35dd6179b1f034d
institution DOAJ
issn 2624-9898
language English
publishDate 2025-03-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Computer Science
spelling doaj-art-1617bfdad0b34cf2a35dd6179b1f034d2025-08-20T03:02:06ZengFrontiers Media S.A.Frontiers in Computer Science2624-98982025-03-01710.3389/fcomp.2025.15395191539519Binary and multiclass malware classification of windows portable executable using classic machine learning and deep learningMoeiz Miraoui0Mohamed Ben Belgacem1Department of Computer Studies, Arab Open University, Riyadh, Saudi ArabiaDepartment of Computer Sciences, ISSAT, University of Gafsa, Gafsa, TunisiaCybersecurity has become a significant concern in recent decades. Enhancing cybersecurity and safeguarding important information systems are essential in today’s world. It is now one of the most important challenges in the realm of IT. Malware has become a significant issue in the modern digital age. The primary objectives of malware are to disrupt, harm, or impair computer systems and information systems without the user’s consent or awareness. Currently, malwares are viewed as some of the most prevalent cyber threats. The prevalence of Windows operating system has made it a prime target for malware attacks. PE (Portable Executable) is the standard file format for executable files and DLLs on Windows systems, with PE malware being the most common form of malicious software. Static analysis, which is mainly a signature-based method for detecting malware, can only identify already known malware. The main weakness of this approach is its struggle with obfuscation, such as encryption and packing. The use of machine learning methods has demonstrated significant potential in the field of malware detection and is an emerging field with many opportunities. Most previous works focus on binary classification, limited number of ML algorithms and even a single dataset. In this paper, we present both a binary and multiclass PE malware classification using four classic machine learning algorithms and four deep learning algorithms. We have applied this algorithm on three publicly available datasets and deduced the best algorithm depending on the number of features and dataset size.https://www.frontiersin.org/articles/10.3389/fcomp.2025.1539519/fullmalwarePE filemachine learningdeep learningclassification
spellingShingle Moeiz Miraoui
Mohamed Ben Belgacem
Binary and multiclass malware classification of windows portable executable using classic machine learning and deep learning
Frontiers in Computer Science
malware
PE file
machine learning
deep learning
classification
title Binary and multiclass malware classification of windows portable executable using classic machine learning and deep learning
title_full Binary and multiclass malware classification of windows portable executable using classic machine learning and deep learning
title_fullStr Binary and multiclass malware classification of windows portable executable using classic machine learning and deep learning
title_full_unstemmed Binary and multiclass malware classification of windows portable executable using classic machine learning and deep learning
title_short Binary and multiclass malware classification of windows portable executable using classic machine learning and deep learning
title_sort binary and multiclass malware classification of windows portable executable using classic machine learning and deep learning
topic malware
PE file
machine learning
deep learning
classification
url https://www.frontiersin.org/articles/10.3389/fcomp.2025.1539519/full
work_keys_str_mv AT moeizmiraoui binaryandmulticlassmalwareclassificationofwindowsportableexecutableusingclassicmachinelearninganddeeplearning
AT mohamedbenbelgacem binaryandmulticlassmalwareclassificationofwindowsportableexecutableusingclassicmachinelearninganddeeplearning