EUVIMEDOpdag EUVIMED
Open access · CC BY-NC-SA 4.0

Analyzing Malware Behavior Using Generative Neural Networks

Wurood A. Jbara, Noor Al-Huda K. Hussein

Al-Noor Journal of Engineering Management and Computer Science · 2026-08-02 · 510-518

DOI: 10.71229/pc796a74 ↗

At a glance

Journal article in Al-Noor Journal of Engineering Management and Computer Science, published online on 2026-08-02. Written by Wurood A. Jbara and 1 co-authors. 21 references. The full text is freely available (open access, CC BY-NC-SA 4.0).

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Traditional detection techniques are struggling with ever-evolving malware threats like zero-day attacks, polymorphic malware, and adversarial samples. Current detection systems (signature-based, heuristic-based, conventional machine learning) fail to generalize to unseen/obfuscated malware variants. In an attempt to overcome these constraints, this paper investigates the possibilities of employing Generative Neural Networks (GNNs), in the form of Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) for the purpose of malware be haviour analysis and detection. We aim to create a novel framework for detecting malware samples that provides some of the best performance in terms of accuracy, precision, and recall while remaining robust to new or unseen malware. This work aims to firstly implement a generative learning-based approach and to measure its adversarial robustness in comparison with the four existing detection techniques. Experimental results show the accuracy, precision, recall of the proposed model is found to be 96.5%, 95.9%, 94.6% with the false positive rate of the model which can be negligible and it is 3.2% which outperforms the traditional machine learning and deep learning models. Our results demonstrate that GNN-based malware detection not only addresses the limitations of conventional approaches in terms of scalability but also provides a more robust and adaptable framework that could be integrated into future real-time threat intelligence and automated defense systems.

Cite

APA

Jbara, W. A., & Hussein, N. A. K. (2026). Analyzing Malware Behavior Using Generative Neural Networks. Al-Noor Journal of Engineering Management and Computer Science, 510-518. https://doi.org/10.71229/pc796a74

Vancouver

Jbara WA, Hussein NAK. Analyzing Malware Behavior Using Generative Neural Networks. Al-Noor Journal of Engineering Management and Computer Science. 2026:510-518. doi:10.71229/pc796a74

BibTeX
@article{Jbara2026,
  author = {Jbara, Wurood A. and Hussein, Noor Al-Huda K.},
  title = {Analyzing Malware Behavior Using Generative Neural Networks},
  journal = {Al-Noor Journal of Engineering Management and Computer Science},
  year = {2026},
  pages = {510--518},
  doi = {10.71229/pc796a74}
}
Start for free →