Skip to content
Open access

AI-Driven Malware Detection: An Entropy-Weighted Ensemble Framework for Static Analysis of Executable Files

Sep 2026 · Computer and Decision Making: An International Journal · 0 citations

TL;DR

A light-weight entropy-weighted ensemble detection approach for static malware detection that combines the predictions of Random Forest, Support Vector Machine and Gradient Boosting classifiers with weights proportional to the validation accuracy of each of these classifiers.

Abstract

Malware remains one of the most common threats to computing infrastructure and attackers are consistently employing obfuscation, packing and polymorphism to evade signature based antiveirus engines. Machine learning (ML) provides an alternative solution that is scalable because it learns discriminative patterns directly from the static and behavioral characteristics of even executable files. This paper introduces a light-weight entropy-weighted ensemble detection approach for static malware detection. The framework uses two simple algorithms to enhance the efficiency and accuracy: (1) an entropy-based feature selection procedure that ranks features according to information gain, and selects only the most discriminative subset of features; (2) a weighted majority voting scheme that combines the predictions of Random Forest, Support Vector Machine (SVM) and Gradient Boosting classifiers with weights proportional to the validation accuracy of each of these classifiers. The methodology proposed is described in detail, and the mathematical formulation of both algorithms is presented. Results are then provided for illustrative examples to show the expected format of the report for accuracy, precision, recall and the effect of the size of the features selected on the detection rate, in three summary tables and two graphs. The framework should be lightweight for computational requirements, compatible with public benchmark dataset like EMBER and Malimg.  

Read PDF

Similar papers

#explainable ai Open access Oct 2026

SHAP driven explainable machine learning for malware classification: From detection to explanation

Detecting malware is a critical aspect of cybersecurity, focused on identifying and preventing malicious software from compromising computer systems. The increasing complexity and sophistication of modern malware often render conventional detection techniques inadequate, necessitating more advanced approaches. In this...

Unknown authors · 0 citations
Open access 2026

A Comparative Analysis of Static Feature Extraction Techniques for PE File Malware Detection using LightGBM and Gradient Boosting Variants

Efficiency of traditional signature-based detection has been severely diminished due to the exponential growth of sophisticated malware. For this reason, the cybersecurity industry has pivoted toward Machine Learning (ML) solutions. This paper presents a comprehensive comparative analysis of machine learning models for...

A. Cvetkovic, Snježana Stanišić, S. Adamovic · 0 citations
2026

AI-Based Malware Behavior Classification and Mitigation System Using Machine Learning

This study proposes an advanced, integrated behavior-based malware classification and automated mitigation framework specifically engineered for Windows operating environments, and introduces a multi-class risk-scoring mechanism to streamline Security Operations Center (SOC) incident triage.

Sivaharish R., S. K., Lediyal S. et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.