Technical gazette, Vol. 33 No. 4, 2026.
Review article
https://doi.org/10.17559/TV-20251009003047
An Overview of Convolutional Neural Network-Based Static Malware Analysis Techniques
Aleksa Komosar
; Faculty of Technical Sciences, University of Novi Sad, Trg Dositeja Obradovića 6, 21000 Novi Sad, Serbia
Milan Gnjatovic
; Department of Information Technology, University of Criminal Investigation and Police Studies, Cara Dušana 196, 11080 Belgrade, Serbia
*
Darko Stefanovic
; Faculty of Technical Sciences, University of Novi Sad, Trg Dositeja Obradovića 6, 21000 Novi Sad, Serbia
Nemanja Macek
; Academy of Technical and Art Applied Studies, School of Electrical and Computer Engineering, Vojvode Stepe 283, 11000 Beograd, Serbia
Dusan Savic
; Faculty of Organizational Sciences, University of Belgrade, Jove Ilića 154, 11010 Belgrade, Serbia
Teodora Vuckovic
; Faculty of Technical Sciences, University of Novi Sad, Trg Dositeja Obradovića 6, 21000 Novi Sad, Serbia
* Corresponding author.
Abstract
This paper provides an overview of convolutional neural network-based static malware analysis techniques. Three research questions are considered: Which architectures based on or related to CNNs are used in static malware analysis? Which datasets are used to support research in this field, and what are the associated challenges? To what extent are the obtained models evaluated? Three scientific databases (Scopus, Web of Science, and MDPI) are searched, and the PRISMA framework is used to conduct and transparently present 70 papers selected according to dedicated inclusion and exclusion criteria. The overview recognizes the recent trend of conceptualizing malware as a sequential structure with both local and long-term dependencies, the need to reconsider the notion of dataset balance, and the need for consistent and transparent application of the F1-score.
Keywords
convolutional neural network; dataset imbalance; F1-score; static malware analysis
Hrčak ID:
348723
URI
Publication date:
30.6.2026.
Visits: 0 *