SavedAdd your journal

Journals / Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi / 2023 / Cilt: 38 - Sayı: 3

Malware Detection Using Image-Based Features and Machine Learning Methods

Görüntü tabanlı özelliklerden ve makine öğrenmesi yöntemlerinden faydalanılarak kötücül yazılım tespiti

Aslıhan GÜNGÖR
İbrahim DOGRU
Necaattin BARIŞÇI
Sinan TOKLU
Pages
1781–1792
Publication Date
2023-01-06
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The results were evaluated using the K-fold crossover validation method, and a highest accuracy rate of 96.72% was obtained with knn and 97.44% with RF.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:As Android devices occupy more of people's lives, they have also become a target of malicious software.
📊
Key Findings & Data:In this study, global features were extracted on the malimg dataset and a feature matrix (2000, 532) long was obtained.
💡
Conclusion & Impact:The results were evaluated using the K-fold crossover validation method, and a highest accuracy rate of 96.72% was obtained with knn and 97.44% with RF.
🔬Design:Modeling & Simulation
📍Scope:2000 Verileri
⚙️Variables:Kötü amaçlı yazılım · görüntü işleme · özellik çıkarılması

Abstract

As Android devices occupy more of people's lives, they have also become a target of malicious software. It is important to detect malicious software and to prevent the losses and damages that may arise from these software. For this purpose, various studies are being carried out about malware detection. Recently, image-based methods and machine learning studies have come to the fore. In these studies, binary files used in static and dynamic analysis are converted into image files. Global and local features extracted from the images are classified by various machine learning methods. In this study, global features were extracted on the malimg dataset and a feature matrix (2000, 532) long was obtained. These features were classified using machine learning methods (LR, LDA, KNN, CART, RF, NB, SVM). The results were evaluated using the K-fold crossover validation method, and a highest accuracy rate of 96.72% was obtained with knn and 97.44% with RF.

Özet

Android cihazların hayatın içinde daha çok yer alması kötü amaçlı yazılımların da hedefi haline gelmesine sebep olmuştur. Kötü amaçlı yazılımların tespit edilmesi ve bu yazılımlardan doğacak kayıpların ve zararların önlenmesi önem arz etmektedir. Bu amaçla kötü amaçlı yazılım tespitine yönelik çeşitli çalışmalar yapılmaktadır. Son zamanlarda görüntüye dayalı yöntemler ve makine öğrenmesi çalışmaları ön plana çıkmaktadır. Bu çalışmalarda statik ve dinamik analizde kullanılan ikili dosyalar görüntü dosyalarına çevrilmektedir. Görüntülerden çıkarılan global ve yerel özellikler çeşitli makine öğrenmesi metotları ile sınıflandırılmaktadır. Bu çalışmada malimg veri seti üzerinde global özellikler çıkarılarak (2000, 532) boyunda bir özellik matrisi elde edilmiştir. Ve bu özellikler makine öğrenme yöntemleri(LR, LDA, KNN, CART, RF, NB, SVM) kullanılarak sınıflandırılmıştır. Sonuçlar K-kat çaprazlama doğrulama yöntemi değerlendirilerek knn ile %96,72 RF ile en yüksek %97,44 doğruluk oranı elde edilmiştir.

🔖

Cite This Article

GÜNGÖR, A., DOGRU, İ., BARIŞÇI, N., TOKLU, S. (2023). Malware Detection Using Image-Based Features and Machine Learning Methods. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, Cilt: 38 - Sayı: 3, 1781–1792. https://ajindex.com/articles/875704

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (5)

  1. Cook S., Malware statistics and facts for 2021. Comparitech https://www.comparitech.com/antivirus/malware-statistics-facts/. Güncelleme Tarihi.Şubat 12, 2021. Erişim Tarihi Nisan 20,2021
  2. Sağıroğlu Ş.,Bulut H.,An Analysıs Of Informatıon And Telecommunıcatıon Securıty In Mobıle Envıronments, Journal Of The Faculty Of Engıneerıng And Archıtecture Of Gazı Unıversıty, Vol.24, No.3, Pp.499-507, 2009 [3] Yajamanam S., Selvin V. R. S., Troia F. D. and Stamp M.,Deep Learning versus Gist Descriptors for Image-based Malware Classification, In Proceedings of the 4th International Conference on Information Systems Security and Privacy (ICISSP 2018), Funchal-Madeira-Portuga, 553-561,22-24 Ocak, 2018 [4] Bhodia N., Prajapati P., Troia F. D. and Stamp M., Transfer Learning for Image-Based Malware Classification. https://arxiv.org/abs/1903.11551.Yayınlanma Tarihi Ocak 21, 2019.Erişim Tarihi Nisan 22,2021
  3. Ünver H. M., Bakour K., Android malware detection based on image‑based features and machine learning techniques. SN Applied Sciences (2020) 2:1299.2020. |
  4. Bakour K., Ünver., H. M.,VisDroid: Android malware classification based on local and global image features, bag of visual words and machine learning techniques, Neural Computing and Applications (2021) 33:3133–3153.2021
  5. Bakour K., Ünver H. M., DeepVisDroid: android malware detection by hybridizing image-based features with deep learning techniques, Neural Computing and Applications,2021 [8] Venkatraman S., Alazab M., Vinayakumar R.,A hybrid deep learning image-based analysis for effective malware detection, Journal of Information Security and Applications 47 (2019) 377–389. 2019 [9] Yuan B., Wang J., Liu D., Guo W., Wu P., Bao X., Byte-level malware classification based on markov images and deep learning,Computers & Security 92 (101740), 2020 [10] Iadarola G., Martinelli F., Mercaldo F. and Santone A., Image-based Malware Family Detection: An Assessment between Feature Extraction and Classification Techniques, In Proceedings of the 5th International Conference on Internet of Things, Big Data and Security (IoTBDS 2020), Online Streaming, 499-506,2020 [11] Naeem H., Ullah F., Naeem M., Khalid S. v.d., Malware detection in industrial internet of things based on hybrid image visualization and deep learning model, Ad Hoc Networks 105 (102154),2020 [12] Angelo G. D’, Ficco M., Palmieri F., Malware detection in mobile environments based on Autoencoders and API-