MALWD&C - A Quick and Accurate Machine Learning-Based Approach for Malware Detection and Categorization

Aug 3, 2026

Upload by Miles

Malware—malicious software—poses serious risks to computer systems and networks, motivating effective prevention of harmful installation. This work presents MALWD&C, a machine learning-based approach that analyzes Portable Executable (PE) files and classifies them as benign or malware. Experiments on a public dataset evaluate multiple classifiers in two-class detection and multi-class categorization settings. Results show Random Forest achieves up to 99.56% (two-class) and 97.69% (multi-class) accuracy, emphasizing speed and improved reliability for academia and industry.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Introduction

Threat landscape and need for protection

Malware injection and Windows PE focus

Existing detection approaches

Proposed MALWD&C overview

applied sciences Article MALWD&C: A Quick and Accurate Machine Learning-Based Approach for Malware Detection and Categorization Attaullah Buriro 1, Abdul Baseer Buriro 2, Tahir Ahmad 3, *, Saifullah Buriro 4 and Subhan Ullah 5 Citation: Buriro, A.; Buriro, A.B.; Ahmad, T.; Buriro, S.; Ullah, S. MALWD&C: A Quick and Accurate Machine Learning-Based Approach for Malware Detection and Categorization. Appl. Sci. 2023, 13, 2508. [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)app13042508 Academic Editors: Konstantinos Rantos, Konstantinos Demertzis and George Drosatos Received: 13 January 2023 Revised: 3 February 2023 Accepted: 13 February 2023 Published: 15 February 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 Faculty of Computer Science, Free University Bozen-Bolzano, 39100 Bolzano, Italy 2 Electrical Engineering Department, Sukkur IBA University, Sukkur 65200, Pakistan 3 Center for Cybersecurity, Brunno Kessler Foundation, 38123 Trento, Italy 4 Faculty of Engineering Science & Technology, Deparment of Electrical Engineering, Indus University Karachi, Karachi 75500, Pakistan 5 Department of Computer Science, National University of Computer and Emerging Sciences (NUCES-FAST), Islamabad 44000, Pakistan * Correspondence: [ahmad@fbk.eu](ahmad@fbk.eu) Abstract: Malware, short for malicious software, is any software program designed to cause harm toa computer or computer network. Malware can take many forms, such as viruses, worms, Trojan horses, and ransomware. Because malware can cause signiﬁcant damage to a computer or network, it is important to avoid its installation to prevent any potential harm. This paper proposes a machine learning-based malware detection method called MALWD&C to allow the secure installation of Programmable Executable (PE) ﬁles. The proposed method uses machine learning classiﬁers to analyze the PE ﬁles and classify them as benign or malware. The proposed MALWD&C scheme was evaluated on a publicly available dataset by applying several machine learning classiﬁers in two settings: two-class classiﬁcation (malware detection) and multi-class classiﬁcation (malware categorization) . The results showed that the Random Forest (RF) classiﬁer outperformed all other chosen classiﬁers, achieving as high as 99.56% and 97.69% accuracies in the two-class and multi-class settings, respectively. We believe that MALWD&C will be widely accepted in academia and industry due to its speed in decision making and higher accuracy. Keywords: malware detection and categorization; pattern matching; binary and multi-class classification 1. Introduction Currently, computers are playing an unavoidable and omnipresent role in our daily lives. They are used for various reasons: storing data, performing research, gaming, social networking, and entertainment, to name a few. However, they are facing continuous, ever-increasing, and constantly evolving cyber security threats. Therefore, it is crucial to implement effective and efﬁcient security measures to protect computers and the sensitive data they contain. One such measure is the use of machine learning-based malware detection methods, such as MALWD&C, to identify and prevent the installation of malicious software on computers. By leveraging the power of machine learning algorithms, these methods can quickly and accurately classify ﬁles as benign or malware, allowing users to install only safe and secure software on their computers. In addition to protecting against cyber security threats, machine learning-based malware detection methods can also help organizations comply with regulations and standards, su

FAQs

What problem does MALWD&C address?

MALWD&C targets the prevention of malicious installation by detecting and categorizing malware in Portable Executable (PE) files for Windows systems.

How does MALWD&C work?

It uses machine learning classifiers to analyze PE files and assign them to benign or malware, and also supports multi-class malware categorization.

Which classifier performed best and what accuracy was reported?

Random Forest outperformed other classifiers, reaching up to 99.56% accuracy for two-class malware detection and 97.69% accuracy for multi-class categorization.

Aug 3, 2026

Upload by Miles