FBAM: A Frequency-Based Attention Mechanism for Enhanced Image-Based Malware Detection

Elgarduh, Anis and Zainal, Anazida and Ghaleb, Fuad A. and Qasem, Sultan Noman and Albarrak, Abdullah M. and Saeed, Faisal (2026) FBAM: A Frequency-Based Attention Mechanism for Enhanced Image-Based Malware Detection. CMES - Computer Modeling in Engineering and Sciences. ISSN 1526-1492

Preview

Text FBAM_revision_clean_1_.pdf - Published Version Available under License Creative Commons Attribution. Download (1MB)

Abstract

The rapid growth and increasing sophistication of malware pose significant challenges to traditional detection methods. Convolutional neural network (CNN)-based malware image classification methods have emerged as a promising approach by transforming binary files into visual representations and enabling automated feature extraction. To enhance discriminative learning, recent studies have incorporated attention mechanisms originally developed for natural image and natural language processing tasks. However, these mechanisms embed inductive biases that assume spatial coherence and visually salient semantics, assumptions that do not necessarily hold in malware image representations, where informative patterns may be subtle, structurally encoded, and globally distributed. To address this representation–mechanism misalignment, this study proposes a Frequency-Based Attention Mechanism (FBAM), a domain-aware module that introduces a frequency-based feature transformation prior to attention computation. By converting feature maps into distribution-aware representations, FBAM enables spatial and channel attention to be guided by statistical feature distributions rather than raw activation magnitudes, allowing more effective capture of malware-specific patterns . FBAM was embedded into seven CNN architectures and evaluated on a dataset comprising 18,060 Windows Portable Executable (PE) files, including both malware and benign samples. Comprehensive experiments were conducted against general-purpose attention modules, including SE, CBAM, and CA, as well as the domain-specific SACNN model. Results demonstrate consistent performance improvements across accuracy, precision, recall, and F1-score. In particular, VGG16 and VGG19 augmented with FBAM achieved accuracies of 98.82% and 98.38%, respectively, outperforming baseline architectures and competing attention mechanisms. These findings provide strong empirical evidence that incorporating distribution-aware frequency information into attention design enhances discriminative feature learning in image-based malware detection.

Item Type:	Article
Identification Number:	10.32604/cmes.2026.080862
Dates:	Date Event 14 May 2026 Accepted 11 June 2026 Published Online
Uncontrolled Keywords:	Malware detection, image-based malware classification, convolutional neural networks, deep learning, attention mechanisms
Subjects:	CAH11 - computing > CAH11-01 - computing > CAH11-01-01 - computer science
Divisions:	Architecture, Built Environment, Computing and Engineering > Computer Science
Depositing User:	Gemma Tonks
Date Deposited:	23 Jun 2026 12:04
Last Modified:	23 Jun 2026 12:08
URI:	https://www.open-access.bcu.ac.uk/id/eprint/17080

Actions (login required)

View Item