Extreme Morphological Learning Machines for the Detection of Windows Malware
Authors:
- Sidney M. Lopes-LimaSLSidney M. Lopes-Lima
- Heverton K. de L. SilvaHSHeverton K. de L. Silva
- João H. da S. LuzJLJoão H. da S. Luz
- Samuel L. de P. SilvaSSSamuel L. de P. Silva
- Hercília J. Do N. LimaHLHercília J. Do N. Lima
- Anna B. A. de AndradeAAAnna B. A. de Andrade
- Alisson M. da SilvaASAlisson M. da Silva
- Washington W. A. da SilvaWSWashington W. A. da Silva
- Wellington P. dos SantosWSWellington P. dos Santos
Open Access
- 11 September 2026
- journal article
- research article
- Published by Springer Nature in SN Computer Science
- Vol. 7 (7) , 747
Abstract
Cyber-attacks are causing billionaires losses in ascending order. Then, our goal is to detect malicious behavior of the suspect executable files, preventively, even previously the file be executed by the client. In this current paper, we propose an antivirus to detect malware utilizing mELM (Morphological Extreme Learning Machine) inspired by Mathematical Morphological image processing theory. Our antivirus software is designed to classify executable applications into two categories: benign and malicious. Our mELMs results were compared with classic ELMs and state-of-the-art antivirus programs. All techniques are assessed through broadly utilized classification measurements. Our mELM, through the Dilation kernel, achieves the best result compared to state-of-the-art. The mELM Dilation kernel achieves an average accuracy of 99.76% in the discrimination between benign and malware executable. We claim that mELM can be adapted to any machine learning dataset. Inspired by Mathematical morphology, our mELMs can model any form that exists in decision-making boundary of the neural network.Keywords
Funding Information
- Universidade Federal de Pernambuco
This publication has 26 references indexed in Scilit:
- Antivirus solution to IoT malware detection with authorial next-generation sandboxThe Journal of Supercomputing, 2024
- Antimalware applied to IoT malware detection based on softcore processor endowed with authorial sandboxJournal of Computer Virology and Hacking Techniques, 2024
- Next-generation antivirus for JavaScript malware detection based on dynamic featuresKnowledge and Information Systems, 2023
- Next-generation antivirus endowed with web-server Sandbox applied to audit fileless attackSoft Computing, 2022
- Morphological extreme learning machines applied to the detection and classification of mammary lesions2021
- Artificial intelligence-based antivirus in order to detect malware preventivelyProgress in Artificial Intelligence, 2020
- DroidDivesDeep: Android Malware Classification via Low Level Monitorable Features with Deep Neural Networks2019
- Analysis of ResNet and GoogleNet models for malware detectionJournal of Computer Virology and Hacking Techniques, 2018
- DroidDelver: An Android Malware Detection System Using Deep Belief Network Based on API Call Blocks2016
- Detection and classification of masses in mammographic images in a multi-kernel approachComputer Methods and Programs in Biomedicine, 2016