Abstract :

Malware Binaries Contain Rich Structural And Behavioral Patterns That Are Often Difficult To Capture Using Traditional Signature-based Or Heuristic Detection Methods. This Work Introduces A Visual Analytics–driven Approach Where Raw Malware Binaries Are Transformed Into Grayscale Image Representations, Enabling Deep Neural Networks To Recognize Subtle Bytelevel Features And Spatial Patterns. By Converting Binary Sequences Into Visual Formats, The System Leverages Convolutional Neural Networks (CNNs) And Hybrid Deep-learning Models To Differentiate Malicious And Benign Samples With Greater Accuracy And Robustness. The Proposed Method Enhances Feature Extraction, Reduces Dependence On Handcrafted Features, And Improves Generalization Against Obfuscated Or Polymorphic Malware. Experimental Evaluations Demonstrate Significant Performance Gains In Detection Precision, Recall, And Overall Classification Reliability, Highlighting Binary Visualization As A Powerful Pathway For Advancing Modern Malware Analysis. Keywords: Malware Visualization, Convolutional Neural Networks (CNNs), Binaryto-image Conversion, Malware Detection, Deep Learning, Obfuscation Resilience, Static Analysis, Visual Feature Extraction, Cybersecurity Analytics, Polymorphic Malware.

Published:

11-12-2025

Issue:

Vol. 25 No. 12 (2025)

Page Nos:

116-122

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite