Using deep learning methods for visualization and detection of malware
Radiotekhnika · 24.12.2025 · (223) · 75-84
DOI: 10.30837/rt.2025.4.223.09 ↗Kurz gefasst
Fachartikel in der Zeitschrift Radiotekhnika, online erschienen am 24.12.2025. Verfasst von O.I. Fediushyn und 4 weiteren Autor:innen.
Abstract (Originalsprache)
The purpose of the article is to conduct a comparative analysis of the effectiveness of common convolutional neural network architectures for the task of classifying malware, which was previously converted into graphic images. The approach is based on converting executable PE-files into grayscale images. The transfer learning method is applied to classify these images. The paper provides an experimental comparison of seven architectures (XceptionNet, DenseNet169, EfficientNetB0, MobileNetV2, InceptionV3, ResNet50V2, and VGG16) based on Accuracy, Precision, Recall, and F1-score metrics to determine the most effective and computationally balanced model for threat analysis. The article will be useful to specialists in the field of cybersecurity and machine learning who are involved in the development of intelligent systems for detecting "zero-day" and polymorphic threats.
Zitieren
APA
Fediushyn, O., Shulik, P., Prosolov, V., Viukhin, D., & Chechui, O. (2025). Using deep learning methods for visualization and detection of malware. Radiotekhnika, 75-84. https://doi.org/10.30837/rt.2025.4.223.09
Vancouver
Fediushyn O, Shulik P, Prosolov V, Viukhin D, Chechui O. Using deep learning methods for visualization and detection of malware. Radiotekhnika. 2025:75-84. doi:10.30837/rt.2025.4.223.09
BibTeX
@article{Fediushyn2025,
author = {Fediushyn, O.I. and Shulik, P.V. and Prosolov, V.V. and Viukhin, D.O. and Chechui, O.V.},
title = {Using deep learning methods for visualization and detection of malware},
journal = {Radiotekhnika},
year = {2025},
number = {223},
pages = {75--84},
doi = {10.30837/rt.2025.4.223.09}
}
EUVIMED