Araştırma Makalesi

A Hybrid Deep Learning Approach for Image-based Malware Classification

Cilt: 5 Sayı: 1 28 Şubat 2026
PDF İndir
TR EN

A Hybrid Deep Learning Approach for Image-based Malware Classification

Öz

The diversity and sophistication of malicious content has significantly impacted end-users of Information and Communication Technologies. In order to mitigate the impact of malicious content, automated deep learning-based techniques have been developed to proactively defend user systems against malware. In this study, we implement a hybrid model for malware detection and classification using the MaleVis dataset. First, feature extraction from the dataset is performed using DenseNet-121, EfficientNet-B0 and ResNet-50 models. These models are deep learning architectures that have been trained on large datasets and are known for their powerful feature extraction capabilities. Each model was used to extract feature vectors from the images in the Malevis dataset. These feature vectors were then merged. The combined feature vectors were used for classification using XGBoost, a powerful classification algorithm. This hybrid model approach combines the feature extraction capabilities of deep learning models with the classification capability of XGBoost to detect malware. Experimental results show that the proposed hybrid model achieves high accuracy rates on the MaleVis dataset. The study shows that combining the feature extraction capabilities of different deep learning models and using these features with a classifier such as XGBoost can provide significant improvements in malware detection and classification.The results demonstrate the model’s potential for integration into real-world threat detection systems.

Anahtar Kelimeler

Destekleyen Kurum

(TUBITAK) Proje No: 122E337

Etik Beyan

Hazırlanan makale için etik kurul onayı gerekmemektedir. Hazırlanan makalede herhangi bir kişi/kurumla çıkar çatışması bulunmamaktadır.

Teşekkür

Bu çalışma, Fırat Üniversitesi Bilimsel Araştırma Projeleri Koordinasyon Birimi (FUBAP) tarafından TEKF 24.27 proje numarası ve Türkiye Bilim ve Teknolojik Araştırma Konseyi (TÜBİTAK) tarafından 122E337 proje numarası ile desteklenmiştir. Ayrıca, yazarlar, yapıcı ve hızlı geri bildirimleriyle bu çalışmanın akademik gelişimine olumlu katkıda bulunan editör(ler)e ve isimsiz hakemlere içtenlikle teşekkür ederler.

Kaynakça

  1. A. Di Nicola, “Towards digital organized crime and digital sociology of organized crime,” Trends Organ. Crime, pp. 1–20, 2022.
  2. Y. Zhang, Y. Xiao, K. Ghaboosi, J. Zhang, and H. Deng, “A survey of cyber crimes,” Secur. Commun. Netw., vol. 5, no. 4, pp. 422–437, 2012.
  3. A. Chakraborty, A. Biswas, and A. K. Khan, “Artificial intelligence for cybersecurity: Threats, attacks and mitigation,” in Artificial Intelligence for Societal Issues. Cham, Switzerland: Springer, 2023, pp. 3–25.
  4. Ö. Aslan, S. S. Aktuğ, M. Ozkan-Okay, A. A. Yilmaz, and E. Akin, “A comprehensive review of cyber security vulnerabilities, threats, attacks, and solutions,” Electron., vol. 12, no. 6, p. 1333, 2023.
  5. E. M. Rudd, A. Rozsa, M. Günther, and T. E. Boult, “A survey of stealth malware attacks, mitigation measures, and steps toward autonomous open world solutions,” IEEE Commun. Surv. Tutor., vol. 19, no. 2, pp. 1145–1172, 2016.
  6. S. S. Chakkaravarthy, D. Sangeetha, and V. Vaidehi, “A survey on malware analysis and mitigation techniques,” Comput. Sci. Rev., vol. 32, pp. 1–23, 2019.
  7. J. G. Heiser, “Understanding today’s malware,” Inf. Secur. Tech. Rep., vol. 9, no. 2, pp. 47–64, 2004.
  8. F. A. Aboaoja, A. Zainal, F. A. Ghaleb, B. A. S. Al-Rimy, T. A. E. Eisa, and A. A. H. Elnour, “Malware detection issues, challenges, and future directions: A survey,” Appl. Sci., vol. 12, no. 17, p. 8482, 2022.

Ayrıntılar

Birincil Dil

İngilizce

Konular

Yazılım Mühendisliği (Diğer)

Bölüm

Araştırma Makalesi

Yayımlanma Tarihi

28 Şubat 2026

Gönderilme Tarihi

10 Kasım 2024

Kabul Tarihi

9 Ağustos 2025

Yayımlandığı Sayı

Yıl 2026 Cilt: 5 Sayı: 1

Kaynak Göster

APA
Metin, Z. B., & Özkaynak, F. (2026). A Hybrid Deep Learning Approach for Image-based Malware Classification. Firat University Journal of Experimental and Computational Engineering, 5(1), 26-43. https://doi.org/10.62520/fujece.1582676
AMA
1.Metin ZB, Özkaynak F. A Hybrid Deep Learning Approach for Image-based Malware Classification. Firat University Journal of Experimental and Computational Engineering. 2026;5(1):26-43. doi:10.62520/fujece.1582676
Chicago
Metin, Zülfiye Beyza, ve Fatih Özkaynak. 2026. “A Hybrid Deep Learning Approach for Image-based Malware Classification”. Firat University Journal of Experimental and Computational Engineering 5 (1): 26-43. https://doi.org/10.62520/fujece.1582676.
EndNote
Metin ZB, Özkaynak F (01 Şubat 2026) A Hybrid Deep Learning Approach for Image-based Malware Classification. Firat University Journal of Experimental and Computational Engineering 5 1 26–43.
IEEE
[1]Z. B. Metin ve F. Özkaynak, “A Hybrid Deep Learning Approach for Image-based Malware Classification”, Firat University Journal of Experimental and Computational Engineering, c. 5, sy 1, ss. 26–43, Şub. 2026, doi: 10.62520/fujece.1582676.
ISNAD
Metin, Zülfiye Beyza - Özkaynak, Fatih. “A Hybrid Deep Learning Approach for Image-based Malware Classification”. Firat University Journal of Experimental and Computational Engineering 5/1 (01 Şubat 2026): 26-43. https://doi.org/10.62520/fujece.1582676.
JAMA
1.Metin ZB, Özkaynak F. A Hybrid Deep Learning Approach for Image-based Malware Classification. Firat University Journal of Experimental and Computational Engineering. 2026;5:26–43.
MLA
Metin, Zülfiye Beyza, ve Fatih Özkaynak. “A Hybrid Deep Learning Approach for Image-based Malware Classification”. Firat University Journal of Experimental and Computational Engineering, c. 5, sy 1, Şubat 2026, ss. 26-43, doi:10.62520/fujece.1582676.
Vancouver
1.Zülfiye Beyza Metin, Fatih Özkaynak. A Hybrid Deep Learning Approach for Image-based Malware Classification. Firat University Journal of Experimental and Computational Engineering. 01 Şubat 2026;5(1):26-43. doi:10.62520/fujece.1582676