Development of an Android-Based Malware Detection Model

Year 2025, Volume: 22 Issue: 2, 73 - 89, 01.11.2025

Ajibola Gbotosho Patrick Ozoh , Tosin Oyetayo

https://izlik.org/JA55YE86KR

Abstract

The study to identify malicious threats in Android mobile phones is presented in this study. The sample Dataset was from DroidFusion-2018—Jupyter Notebook, together with Python for implementation. The techniques considered include the classifiers mentioned in the study. An ensemble of techniques was developed for the study. The Ensemble model achieved 97% accuracy, compared to 71%, 77%, and 79% attained by SVM, KNN, and RF. The study designed a model for detecting malicious Android applications that are integrated into existing malware detection platforms to improve their usage and acceptance.

Keywords

Android , malicious threats , machine learning , manifest analysis

References

• J. Hightower, W. B. Glisson, R. Benton, and J. T. McDonald, “Classifying Android Applications Via System Stats,” IEEE International Conference on Big Data (Big Data), virtual, 2021 pp. 5388-5394, doi:10.1109/BigData52589.2021.9671999.
• J. Wallen, "Why is Android more popular globally, while iOS rules the US," 2021, www. techrepublic.com/article/why-is-android-more-popular-globally-while-ios-rules-the-us.
• D. O. Sahin, S. Akleylek, and E. Kilic, “LinRegDroid: Detection of Android Malware Using Multiple Linear Regression Models-Based Classifiers,” IEEE Access, vol. 10, pp. 14246–14259, Jan.2022, doi:10.1109/ACCESS.2022.3146363.
• D. Gibert, M. Carles, and P., "The rise of machine learning for detection and classification of malware: Research developments, trends and challenges," J. Netw. Comput. Appl., vol. 153, pp. 102526, Mar. 2020, doi:10.1016/j.jnca.2019.102526.
• J. Vijayan, “Android Malware Hijacks Phone Shutdown Routine,” Security Intelligence, 2021, securityintelligence.com/news/android-malware-hijacks-phone-shutdown-routine/.
• R. Jusoh, A. Firdaus, S. Anwar, M. Z. Osman, M. F. Darmawan, and M. F. A. Razak, “Malware Detection Using Static Analysis in Android: a review of FeCO (Features, Classification, and Obfuscation),” PeerJ Comput. Sci., vol. 7, pp. 1–54, Jun. 2021, doi:10.7717/peerj-cs.522.
• J. Senanayake, H. Kalutarage, and M. O. Al-Kadri. “Android mobile malware detection using machine learning: A systematic review”, Electronics, vol. 10, no. 13, 1606, 2021, doi:10.3390/electronics10131606.
• O. Yildiz, and I. A. Doǧru, “Permission-based Android Malware Detection System Using Feature Selection with Genetic Algorithm,'' Int. J. Softw. Eng. Knowl. Eng., 29, no. 2, pp. 245–262, 2019, doi:10.1142/S0218194019500116.
• H. A. Alatwi, “Android Malware Detection Using Category-Based Machine Learning Classifiers,” 2016, www. scholarworks.rit.edu/theses.
• F. Tchakounte, “A Malware Detection System for Android Malware Detection based on Android Permissions View project IoT security,” 2016, www.researchgate.net/publication/282866516.
• M. S. Alhebsi, “Android Malware Detection using Machine Learning Techniques,” 2022, www.scholarworks.rit.edu/theses.
• E. Masabo, “A Feature Engineering Approach for Classification and Detection of Polymorphic Malware using Machine Learning,” Ph.D. dissertation, Depart. Comp. Networks, Sch. Computing and Inform. Tech., Makerere Uni., Kampala, 2019.
• V. Kouliaridis, and G. Kambourakis, “A comprehensive survey on machine learning techniques for android malware detection,” Information 2021, vol. 12, 185, Apr. 2021, doi:10.3390/info12050185.
• F. Akbar, M. Hussain, R. Mumtaz, Q. Riaz, A. Wahab, and K. H. Jung, “Permissions-Based Detection of Android Malware Using Machine Learning,” Symmetry, vol. 14, no. 4, pp. 718, Apr. 2022, doi:10.3390/sym14040718.
• Y. Kamalrul Bin Mohamed Yunus, and S. bin Ngah, “Review of Hybrid Analysis Technique for Malware Detection,” IOP Conf. Ser.: Mater. Sci. Eng., vol. 769, no. 1, 012075, Jun. 2020, doi:10.1088/1757899X/769/1/012075.
• A. Muzaffar, H. Ragab Hassen, M. A. Lones, and H. Zantout, “An in-depth review of machine learning based Android malware detection,” Comput. Secur., vol. 121, 102833,Jul. 2022, doi:10.1016/j.cose.2022.102833.
• E. Amer, S. E. Mohamed, M. Ashaf, A. Ehab, O. Shereef, H. Metwaie, and A. Mohammed, “Using Machine Learning to Identify Android Malware Relying on API calling sequences and Permissions,” J. Comput. Commun., vol. 1, no. 1, pp. 38-47, Feb. 2022, doi: 10.21608/jocc.2022.218454.
• A. S. Shatnawi, Q. Yassen, and A. Yateem, “An Android Malware Detection Approach Based on Static Feature Analysis Using Machine Learning Algorithms,” Procedia Comput. Sci., vol. 201, pp. 653–658, Nov. 2022, doi:10.1016/j.procs.2022.03.086.
• D. O. Sahin, S. Akleylek, and E. Kilic, “LinRegDroid: Detection of Android Malware Using Multiple Linear Regression Models-Based Classifiers,” IEEE Access, vol. 10, pp. 14246–14259, Jan. 2022, doi:10.1109/ACCESS.2022.3146363.
• H. Li, H. Zhang, X. Chen, D. Liao, and M. Zhang, “Android Malware Detection Based on Sensitive Patterns,” Research Square, 2022, doi : 10.21203/rs.3.rs-1592245/v1.
• N. Sarah, F. Y. Rifat, M. S. Hossain, and H. S. Narman, “An Efficient Android Malware Prediction Using Ensemble machine learning algorithm,” Procedia Comput. Sci., vol. 191, no.1, pp. 184–191, Jan. 2021, doi:10.1016/j.procs.2021.07.023.
• D. O. Şahin, O. E. Kural, S. Akleylek, and E. Kılıç, “A novel permission-based Android malware detection system using feature selection based on linear regression,” Neural Comput. Appl., vol.35, no.5, pp. 1-16, Mar. 2021, doi:10.1007/s00521-021- 05875-1.
• E. H. Houssein, M. E. Hosney, M. Elhoseny, D. Oliva, W. M. Mohamed, and M. Hassaballah, “Hybrid Harris hawks optimization with cuckoo search for drug design and discovery in chemoinformatics,” Scientific Reports, vol. 10, no. 1, 14439, Sept. 2020, doi:10.1038/s41598-020-71502-z.
• Q. Cao, L. La, H. Liu and S. Han, “Mixed weighted KNN for imbalanced datasets,” Int. J. Performability Eng., vol. 14, no. 7, pp. 1391-1400, 2018. doi: 10.23940/ijpe.18.07.p2.13911400.
• H. K. Almulla, H. J. Mohammed, N. Clarke, A. A. Hadi,and M. A. Mohammed, “An Effective Feature Optimization Model for Android Malware Detection,’’ Mesop. J. CyberSecur., vol. 5, no. 2, pp. 563-576, 2025.doi: 10.58496/MJCS/2025/034.
• R.Verma, “Review of Malware Detection from Android based Smart Mobile for Cyber Security”, 2025.
• A. K. Nair, and D. Gupta, “AndroIDS: Android-based Intrusion Detection System using Federated Learning,” arXiv preprint arXiv:2506.17349. Accessed: June 2025. [Online] Available: https://www.arxiv.org/pdf/2506.17349.
• F. Nawshin, D. Unal, M. Hammoudeh, and P. N. Suganthan, “A Novel Genetic Algorithm Optimized Adversarial Attack in Federated Learning for Android-Based Mobile Systems”, IEEE Trans. Consum. Electron., vol. 99, pp.1-1, Jun. 2025, doi: 10.1109/TCE.2025.3577905.
• S. Nethala, P. Chopra, K. Kamaluddin, S. Alam, S. Alharbi, and M. Alsaffar, “A Deep Learning-Based ensemble framework for robust Android malware detection”, IEEE Access, vol. 13, pp. 46673-46696, Mar. 2025, doi: 10.1109/ACCESS.2025.3551152.
• I. Nawaz, S. N. Khosa, R. Fatima, M. Saeed, and M. S. A. Hashmi, “Smart Filters For Sms Spam: A Machine Learning Approach to Sms Classification,” Spectr. Eng. Sci. , vol. 3, no. 5, pp. 71-98, May 2025, doi: 10.5281/zenodo.15333801.
• N. Hafidi, Z. Khoudi, M. Nachaoui, and S. Lyaqini, “Enhanced SMS spam classification using machine learning with optimized hyperparameters,” Indonesian J. Electr. Eng. Comput. Sci, vol. 37, no. 1, pp. 356- 364, Jan. 2025. doi: 10.11591/ijeecs.v37.i1.pp356-364.
• N. Durshatti, and O. Sraani, “Spam Message Detection with Multiple Algorithms,” SSRN. Accessed: 16 May. [Online] Available: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5183187.
• J. K. Prasad, and S. Christy, “SMS spam detection using multinational Naive Bayes algorithm compared with K nearest neighbor algorithm,” in AIP Conference Proceedings, vol. 3270, no. 1, pp. 020090, AIP Publishing LLC, 2025.
• A. B. Ahmed, and K. Haruna, “Enhanced Sms Spam Detection Using Bernoulli Naive Bayes With Tf-Idf,’’ FUDJSE, vol. 9, no. 1, pp. 393-399, Apr. 2025, doi:10.33003/fjs-2025-0901-3226.
• P. Ozoh, M. Ibrahim, R. Ojo, A. Sunmade, and T. Oyetayo, “SMS Spam Detection Using Machine Learning Approach,” International STEM Journal, vol. 6, no. 1, pp. 10-27, Jun. 2025.
• M. F. Johari, K. L. Chiew, A. R. Hosen, K. S. Yong, A. S. Khan, I. A. Abbasi,D. Grzonka, “Key insights into recommended SMS spam detection datasets,” Sci. Rep., vol. 15, 8162, Mar. 2025, doi:10.1038/s41598-025-922231.
• H. Xu, A. Qadir, and S. Sadiq, “Malicious SMS detection using ensemble learning and SMOTE to improve mobile cybersecurity,” Comput. Secur., vol. 154, 104443, Mar. 2025, doi:10.1016/j.cose.2025.104443.
• M. A. Bouke, O. I. Alramli, and A. Abdullah, “XAIRF-WFP: a novel XAI-based random forest classifier for advanced email spam detection”, Int. J. Inf. Secur., vol. 24, no. 1, pp.1-5, Oct. 2025, doi:10.1007/s10207-02400920-1.
• A. Madhulatha, A. K. Das, S. C. Bhan, M. Mohapatra, D.S. Pai, D. R. Pattanaik, and P. Mukhopadhyay, “Feasibility of model output statistics (MOS) for improving the quantitative precipitation forecasts of IMD GFS model,” J. Hydrol., vol. 649, 132454, Mar. 2025, doi: 10.1016/j.jhydrol.2024.132454.
• M. Ahmadi, M. Khajavi, A.Varmaghani, A. Ala, K., Danesh, and D. Javaheri, ”Leveraging large language models for cybersecurity: enhancing sms spam detection with robust and context-aware text classification,” arXiv preprint arXiv:2502.11014, 2025.
• L. Shen, Y. Wang, Z. Li, and W. Ma, “SMS Spam Detection Using BERT and Multi-Graph Convolutional Networks,” Int. J. Intell. Netw.., vol.6, pp. 79-88, 2025, doi: 10.1016/j.ijin.2025.06.002.
• A. Langenbucher, N. Szentmáry, J. Wendelstein, A. Cayless, P. Hoffmann, and D. Gatinel, “Performance evaluation of a simple strategy to optimize formula constants for zero mean or minimal standard deviation or root-meansquared prediction error in intraocular lens power calculation,” Am. J. Ophthalmol., vol. 269, pp. 282-292, Jan. 2025, doi: 10.1016/j.ajo.2024.08.043.
• A. R. Elkilany and Y. B. Chu, “Elucidation on the performance of various machine learning models for real- time malware detection, malware classification and network packet screening,” ML Comput. Sci. Eng., vol 1, 9, Jan. 2025, doi: 10.1007/s44379-024-00010-y.
• R. N. Al Ogaili, O. A. Raheem, M. H. G. Abdkhaleq, Z. A. A. Alyasseri, S. A. A. A Alsaidi, A. H. Alsaeedi and S. Manickam, “AntDroidNet Cybersecurity Model: A Hybrid Integration of Ant Colony Optimization and Deep Neural Networks for Android Malware Detection,” Mesop. J. CyberSecur., vol. 5, no. 1, pp. 104-120, Feb. 2025, doi: 10.58496/MJCS/2025/008.
• C. Devika, C. C. Chowdary, D. Ramji, B. Tharun, and C. Nalini, “A framework to detect malware using a mobile edge computing system with minimal latency,” in Hybrid and Advanced Technologies, S. Prasad Jones Christydass, Nurhayati Nurhayati, S. Kannadhasan, Eds., CRC Press, vol.2, 2025, pp. 473-478.
• B. Ajayi, B. Barakat, and K. McGarry, “Leveraging VAE-Derived Latent Spaces for Enhanced Malware Detection with Machine Learning Classifiers,” arXiv preprint arXiv:2503.20803. Accessed: 30 April 2025. [Online] Available: https://arxiv.org/pdf/2503.20803.