A novel YOLO-NAS algorithm for android malware detection using histogram of oriented gradients (HOG) based feature extraction
DOI:
https://doi.org/10.65746/jbrha73Keywords:
android malware detection; deep learning; YOLO-NAS; histogram of oriented gradients (HOG); accuracyAbstract
Smartphones have developed into more than just communication tools in the current digital era, becoming essential to many facets of daily life. Because of its large user base and open-source nature, Android is a dominant mobile operating system. But because of its extensive use, it has become a prominent target for more complex malware attacks. This efficient deep learning-based framework for Android virus detection uses a proposed You Only Look Once based Neural Architecture Search (YOLO-NAS) model in conjunction with feature selection techniques. The system first receives a dataset of Android malware, after which data preparation is carried out to enhance data quality, remove noise, and standardize features. A Histogram of Oriented Gradients (HOG) model is used to identify the most pertinent and discriminative features from the processed dataset in order to decrease dimensionality and increase computing efficiency. The YOLO-NAS model, which classifies malware in a two-class environment as either benign or malicious, is then fed the enhanced feature set. The proposed YOLO-NAS concept aims to improve detection accuracy without compromising robustness or scalability. Performance is assessed using common measures such as F1-Score, Accuracy, Precision, and Recall. The suggested method is appropriate for real-time Android security applications since testing results show that YOLO-NAS and enhanced feature extraction greatly enhance malware detection capabilities.
References
1. Qiu J, Zhang J, Luo W, et al. A survey of android malware detection with deep neural models. ACM Computing Surveys (CSUR). 2020; 53(6): 1–36. doi: 10.1145/3417978
2. Qian X, Zheng X, He Y, et al. Lamd: Context-driven android malware detection and classification with llms. 2025 IEEE Security and Privacy Workshops (SPW). IEEE; 2025. pp. 126–136. doi: 10.1109/SPW67851.2025.00017
3. Liu Z, Wang R, Japkowicz N, et al. SeGDroid: An Android malware detection method based on sensitive function call graph learning. Expert Systems with Applications. 2024; 235: 121125. doi: 10.1016/j.eswa.2023.121125
4. Kim J, Ban Y, Ko E, et al. MAPAS: A practical deep learning-based android malware detection system. International Journal of Information Security. 2022; 21(4): 725–738. doi: 10.1007/s10207-022-00579-6
5. Odusami M, Abayomi-Alli O, Misra S, et al. Android malware detection: A survey. International conference on applied informatics. Cham: Springer International Publishing; 2018. pp. 255–266. doi: 10.1007/978-3-030-01535-0_19
6. Mallidi S. Bat optimization algorithm for wrapper‐based feature selection and performance improvement of android malware detection. IET Networks (Wiley-Blackwell). 2021; 10(3). doi: 10.1049/ntw2.12022
7. Abubaker H, Ali A, Shamsuddin SM, Hassan S. Exploring permissions in android applications using ensemble-based extra tree feature selection. Indonesian Journal of Electrical Engineering and Computer Science. 2020; 19(1): 543–552. doi: 10.11591/ijeecs.v19.i1.pp543-552
8. Zhang S, Su H, Liu H, et al. MPDroid: A multimodal pre-training Android malware detection method with static and dynamic features. Computers & Security. 2025; 150: 104262. doi: 10.1016/j.cose.2024.104262
9. Habeeb MA, Khaleel Y. Enhanced android malware detection through artificial neural networks technique. Mesopotamian Journal of CyberSecurity. 2025; 5(1): 62–77. doi: 10.58496/MJCS/2025/005
10. Mahindru A, Sangal AL. Deepdroid: Feature selection approach to detect android malware using deep learning. In 2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS). IEEE; 2019. pp. 16–19. doi: 10.1109/ICSESS47205.2019.9040821
11. Çalık Bayazıt E, Şahingöz ÖK, Doğan B. A deep learning based android malware detection system with static analysis; 2022. pp. 1–6.
12. Wasif MS, Miah MP, Hossain MS, et al. “CNN-ViT synergy: An efficient Android malware detection approach through deep learning.” Computers and Electrical Engineering. 2025; 123: 110039. doi: 10.1016/j.compeleceng.2024.110039
13. Vinayakumar R, Alaza M, Soman KP, et al. Robust intelligent malware detection using deep learning. IEEE Access. 2019; 7: 46717–46738. doi: 10.1109/ACCESS.2019.2906934
14. Gopinath M, Sethuraman SC. A comprehensive survey on deep learning based malware detection techniques. Computer Science Review. 2023; 47: 100529. doi: 10.1016/j.cosrev.2022.100529
15. Abualhassan Z, Hassan E, Husni D, et al. Malware recognition using novel convolutional neural network with residual connections. International Journal of Machine Learning and Cybernetics. 2026; 17(3): 86. doi: 10.1007/s13042-025-02815-6
16. Musa HO, Muhanad TY. “Effective android malware detection using CNN and LSTM Model with GWO-Based feature selection.” Babylonian Journal of Machine Learnin. 2026; (2026): 1–22. doi: 10.58496/BJML/2026/001
17. Lo WW, Layeghy S, Sarhan M, et al. Graph neural network-based android malware classification with jumping knowledge. 2022 IEEE Conference on Dependable and Secure Computing (DSC). IEEE; 2022. pp. 1–9. doi: 10.1109/DSC54232.2022.9888878
Downloads
Published
Data Availability Statement
The authors received no financial support from any funding agency, institution, or organization for this research work.
Issue
Section
License
Copyright (c) 2026 Shanmuga Priya Gopalakrishnan, Rama Subra Mani Vanamamalai (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
