A lightweight hybrid CNN–vision transformer framework for image-based Android malware detection
4 affiliations
- 1School of Computer Science and Engineering, , Vellore,
- 2Department of Electronics and Communication Engineering, Alliance School of Applied Engineering, , Bengaluru,
- 3Department of CSE, , Vijayawada,
- 4Department of Electronics and Communication Engineering, , Bhaktapur,
Abstract
The rapid development of android applications has been accompanied by a consistent outpouring in sophisticated malware variations that progressively elude signature-based and traditional machine learning detection systems. While considering deep learning models like convolutional and recurrent neural networks, improved results are attained but they rely on local feature extraction and lack in modelling long-range dependencies which limit their adaptability towards advanced obfuscated and polymorphic malwares. In this research work, a lightweight hybrid malware detection framework is proposed which combines MobileNetV2 and a Vision Transformer (ViT) to empower effective and strong Android malware classification from image-based depictions of application binaries. Compact spatial features are extracted by MobileNetV2 and global contextual relationships are captured using self-attention mechanisms by Vision Transformer. Thus, this hybrid design attains effective balance between computational efficiency and detection accuracy. By leveraging the large-scale MalNet dataset comprised of 8 android malware families, the proposed model is evaluated and experimental results presents 98% accuracy, precision, recall, and F1-score by outperforming recent proposed methods based on CNN, transformer, and hybrid baselines. It proves our proposed model maintains compact model size and low inference latency. Further, the results demonstrate that this integration will provide appropriate deployment solution for android malware detection especially real-time security operations which are resource constrained.
Related
- An Explainable Multi-Criteria Decision-Making Framework for Evaluating Malware Detection Models Across Heterogeneous Datasets
- A domain knowledge-enhanced lightweight transformer for automatic identification of land-use conflicts in territorial spatial planning texts
- A lightweight blockchain-inspired hybrid intrusion detection system with ensemble learning for tamper-proof auditing
- FAnet: A lightweight end-to-end framework for Fructus Aurantii identification and quality grading
- Context-Aware Detection of Content Evidencing Illegal or Predatory Fintech Lending Practices on Indonesian Digital Platforms Using Transformer-Based Language Models
BibTeX
@article{mani2026lightweight,
title = {{A lightweight hybrid CNN–vision transformer framework for image-based Android malware detection}},
author = {Gopinath Mani and SatheeshKumar Palanisamy and Gnana Sri Manasa Veeramachaneni and Aditya Ram Manam and Sajid Khan Mohammed and Sachin Shrestha},
journal = {Journal of Algorithms \& Computational Technology},
year = {2026},
month = oct,
doi = {10.1177/17483026261500725},
url = {https://doi.org/10.1177/17483026261500725},
note = {CC BY},
}
RIS
TY - JOUR
TI - A lightweight hybrid CNN–vision transformer framework for image-based Android malware detection
AU - Gopinath Mani
AU - SatheeshKumar Palanisamy
AU - Gnana Sri Manasa Veeramachaneni
AU - Aditya Ram Manam
AU - Sajid Khan Mohammed
AU - Sachin Shrestha
PY - 2026
DA - 2026/10/23
JO - Journal of Algorithms & Computational Technology
DO - 10.1177/17483026261500725
UR - https://doi.org/10.1177/17483026261500725
AB - The rapid development of android applications has been accompanied by a consistent outpouring in sophisticated malware variations that progressively elude signature-based and traditional machine learning detection systems. While considering deep learning models like convolutional and recurrent neural networks, improved results are attained but they rely on local feature extraction and lack in modelling long-range dependencies which limit their adaptability towards advanced obfuscated and polymorphic malwares. In this research work, a lightweight hybrid malware detection framework is proposed which combines MobileNetV2 and a Vision Transformer (ViT) to empower effective and strong Android malware classification from image-based depictions of application binaries. Compact spatial features are extracted by MobileNetV2 and global contextual relationships are captured using self-attention mechanisms by Vision Transformer. Thus, this hybrid design attains effective balance between computational efficiency and detection accuracy. By leveraging the large-scale MalNet dataset comprised of 8 android malware families, the proposed model is evaluated and experimental results presents 98% accuracy, precision, recall, and F1-score by outperforming recent proposed methods based on CNN, transformer, and hybrid baselines. It proves our proposed model maintains compact model size and low inference latency. Further, the results demonstrate that this integration will provide appropriate deployment solution for android malware detection especially real-time security operations which are resource constrained.
SN - 1748-3026
SN - 1748-3018
ER -