Interval Valued Neutrosophic Set with Machine Learning Model  Dynamic Malware Detection in Digital Security

Mohanad Mousa Janat; Ahmed A El-Douh; Ahmed Abdelhafeez; Hanadi Ahmad Simmak

Authors

Mohanad Mousa Janat Medical Physics Department, College of Science, Ashur University, Baghdad, Iraq
Ahmed A El-Douh College of Informatics, Midocean University, 98123, Moroni, Comoros; Applied Science Research Center, Applied Science Private University, Amman
Ahmed Abdelhafeez Computer Science Department, Faculty of Information Systems and Computer Science, October 6 University, Giza, 12585, Egypt; Applied Science Research Center, Applied Science Private University, Amman
Hanadi Ahmad Simmak Communication Engineering Department, Electrical and Electronic Engineering Faculty, Aleppo University, Syria

Keywords:

Malware Classification and Detection; Security; Interval Valued Neutrosophic Set; Machine Learning Model.

Abstract

Traditional signature-based detection techniques are useless against new forms of
malware due to their fast development, which poses a serious cybersecurity risk. People,
businesses, and governments are all affected by this expanding threat, highlighting the urgent
need for robust malware detection systems. Due to their reliance on predetermined signatures,
traditional machine learning-based techniques frequently fail to identify threats that have not yet
been identified and instead rely on static and dynamic malware analysis. To improve malware
detection performance across a variety of datasets, this study assesses traditional ML. Interval
Valued Neutrosophic Set (IVNS) is used in this study to overcome vague information. The
Neutrosophic Model is used to evaluate and rank six ML models. The results show support vector
machine is the best ML Model for dynamic malware detection in digital security.

DOI: 10.5281/zenodo.15776437