Image-Based Approach for Android Malware Detection Using APK Component Fusion and Deep Learning
Authors:
- 15 May 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Abstract
The increase of Android malware, coupled with the growing sophistication of obfuscation techniques, underscores the critical need for advanced detection mechanisms. An innovative method is introdcued that converts essential APK components—namely, classes.dex (Dalvik executable), AndroidManifest.xml (manifest and configuration files), and resources.arsc (compiled resources)—into grayscale images. Incremental feature fusion is then applied to integrate both individual and combined components, allowing a comprehensive assessment of their impact on detection performance. The CICMalDroid 2020 dataset was employed to evaluate multiple convolutional neural network (CNN) architectures, with ResNet50 achieving the best results. The model attained an accuracy of 98.83%, a precision of 99.27%, and a recall of 99.15%, demonstrating the effectiveness of feature integration and deep learning techniques in overcoming obfuscation challenges and offering a robust solution for real-world Android malware detection systems.Keywords
This publication has 28 references indexed in Scilit:
- An Overview of Techniques for Obfuscated Android Malware DetectionSN Computer Science, 2024
- AndroDex: Android Dex Images of Obfuscated MalwareScientific Data, 2024
- EvadeDroid: A practical evasion attack on machine learning for black-box Android malware detectionComputers & Security, 2023
- MDLDroid: Multimodal Deep Learning Based Android Malware Detection2023
- A Lightweight and Multi-Stage Approach for Android Malware Detection Using Non-Invasive Machine Learning TechniquesIEEE Access, 2023
- BLADE: Robust malware detection against obfuscation in androidForensic Science International: Digital Investigation, 2021
- Android Malware Detection Using Deep LearningProcedia Computer Science, 2021
- Android malware detection method based on bytecode imageJournal of Ambient Intelligence and Humanized Computing, 2020
- Evaluation of Resource-Based App Repackaging Detection in Android2016
- Going deeper with convolutions2015