Android Malware Detection with Hybrid Feature Selection and Bayesian Optimization
DOI:
https://doi.org/10.59395/ijadis.v7i1.1526Keywords:
Android Malware detection, Hybrid feature selection, Bayesian optimization, Machine Learning, DREBIN-215Abstract
The increasing dimensionality of Android application features poses significant challenges for accurate and efficient malware detection. This study proposes a hybrid feature selection framework that combines Minimum Redundancy Maximum Relevance (mRMR) and correlation filtering to optimize classification performance on the Drebin-215 dataset. A selected configuration of 175 features with a correlation threshold of 0.7 was evaluated using five classifiers: LSTM, Support Vector Machine (SVM), Random Forest, K-Nearest Neighbors (KNN), and XGBoost. The experimental results show that dimensionality reduction improves classification stability and overall predictive performance. SVM exhibits the most notable improvement, with accuracy increasing from 63.05% without feature selection to 98.57% after applying the proposed framework. LSTM achieves 98.57% accuracy with an AUC of 99.86%, while Random Forest, KNN, and XGBoost consistently achieve accuracy above 97%. In addition to performance enhancement, the hybrid feature selection approach substantially improves computational efficiency. SVM training time decreases from 770.75 seconds to 155.88 seconds, and testing time is reduced from 15.581 seconds to 0.3824 seconds. KNN testing time also decreases from 1.623 seconds to 0.4595 seconds..
Downloads
References
[1] E. K. Ylmaz and H. Bakr, Hyperparameter tuning and feature selection methods for malware detection, Journal of Polytechnic, vol. 27, no. 1, pp. 343353, 2024, doi: 10.2339/politeknik.1243881. DOI: https://doi.org/10.2339/politeknik.1243881
[2] A. Dalolu and . A. Doru, Android letim Sisteminde Ktcl Yazlm Tespit Sistemleri, DMF Mhendislik Dergisi, vol. 11, no. 2, pp. 499511, 2020, doi: 10.24012/dumf.559205. DOI: https://doi.org/10.24012/dumf.559205
[3] McAfee, Mobile Threat Report 2021. [Online]. Available: https://www.mcafee.com/content/dam/global/infographics/McAfeeMobileThreatReport2021.pdf.
[4] C. S. Yadav, J. Singh, A. Yadav, H. S. Pattanayak, R. Kumar, A. A. Khan, M. A. Haq, A. Alhussen, and S. Alharby, Malware analysis in IoT & Android systems, Electronics, vol. 11, no. 15, p. 2354, 2022, doi: 10.3390/electronics11152354. DOI: https://doi.org/10.3390/electronics11152354
[5] A. Al-Marghilani, Comprehensive analysis of IoT malware evasion techniques, Engineering, Technology & Applied Science Research, vol. 11, no. 4, pp. 74957500, 2021, doi: 10.48084/etasr.4296. DOI: https://doi.org/10.48084/etasr.4296
[6] V. Kouliaridis, G. Kambourakis, D. Geneiatakis, and N. Potha, Two anatomists are better than oneDual-level Android malware detection, Symmetry, vol. 12, p. 1128, 2020, doi: 10.3390/sym12071128. DOI: https://doi.org/10.3390/sym12071128
[7] A. Alhussen, Advanced Android malware detection through deep learning optimization, Engineering, Technology & Applied Science Research, vol. 14, no. 3, pp. 1455214557, 2024, doi: 10.48084/etasr.7443. DOI: https://doi.org/10.48084/etasr.7443
[8] G. A. Pradipta, R. Wardoyo, A. Musdholifah, and I. N. Sanjaya, Radius-SMOTE: A new oversampling technique of minority samples based on radius distance for learning from imbalanced data, IEEE Access, vol. 9, pp. 7476374777, 2021, doi: 10.1109/ACCESS.2021.3080316. DOI: https://doi.org/10.1109/ACCESS.2021.3080316
[9] M. Kamaladevi, V. Venkataraman, and K. Sekar, Tomek link undersampling with stacked ensemble classifier for imbalanced data classification, Annals of the Romanian Society for Cell Biology, vol. 25, no. 4, pp. 21822190, 2021. [Online]. Available: http://annalsofrscb.ro/index.php/journal/article/view/2751/2283
[10] Z. Xu, D. Shen, T. Nie, and Y. Kou, A hybrid sampling algorithm combining M-SMOTE and ENN based on random forest for medical imbalanced data, Journal of Biomedical Informatics, vol. 107, p. 103465, Jul. 2020, doi: 10.1016/j.jbi.2020.103465. DOI: https://doi.org/10.1016/j.jbi.2020.103465
[11] H. Hairani, A. Anggrawan, and D. Priyanto, Improvement performance of the random forest method on unbalanced diabetes data classification using SMOTE-Tomek link, International Journal on Informatics Visualization, vol. 7, no. 1, pp. 258264, 2023, doi: 10.30630/joiv.7.1.1069. DOI: https://doi.org/10.30630/joiv.7.1.1069
[12] S. H. Imanuddin, K. Adi, and R. Gernowo, Sentiment analysis on Satusehat application using support vector machine method, Journal of Electronics, Electromedical Engineering, and Medical Informatics, vol. 5, no. 3, pp. 143149, 2023, doi: 10.35882/jeemi.v5i3.304. DOI: https://doi.org/10.35882/jeemi.v5i3.304
[13] A. Dhiyaussalam, F. A. Wibowo, E. A. Sarwoko, and I. M. A. Setiawan, Classification of headache disorder using random forest algorithm, in Proc. 4th Int. Conf. Informatics and Computational Sciences (ICICoS), 2020, doi: 10.1109/ICICoS51170.2020.9299105. DOI: https://doi.org/10.1109/ICICoS51170.2020.9299105
[14] G. Mitrentsis and H. Lens, An interpretable probabilistic model for short-term solar power forecasting using natural gradient boosting, Applied Energy, vol. 309, p. 118473, Mar. 2022, doi: 10.1016/j.apenergy.2021.118473. DOI: https://doi.org/10.1016/j.apenergy.2021.118473
[15] C. Bentjac, A. Csrg, and G. Martnez-Muoz, A comparative analysis of gradient boosting algorithms, Artificial Intelligence Review, vol. 54, no. 3, 2020, doi: 10.1007/s10462-020-09896-5. DOI: https://doi.org/10.1007/s10462-020-09896-5
[16] R. Huang et al., Well performance prediction based on long short-term memory (LSTM) neural network, Journal of Petroleum Science and Engineering, vol. 208, p. 109686, Jan. 2022, doi: 10.1016/j.petrol.2021.109686. DOI: https://doi.org/10.1016/j.petrol.2021.109686
[17] W. Zhang, C. Wu, H. Zhong, Y. Li, and L. Wang, Prediction of undrained shear strength using extreme gradient boosting and random forest based on Bayesian optimization, Geoscience Frontiers, vol. 12, pp. 469477, 2021, doi: 10.1016/j.gsf.2020.03.007. DOI: https://doi.org/10.1016/j.gsf.2020.03.007
[18] L. D. Hansen, M. Stokholm-Bjerregaard, and P. Durdevic, Modeling phosphorous dynamics in a wastewater treatment process using Bayesian optimized LSTM, Computers and Chemical Engineering, vol. 160, p. 107738, 2022, doi: 10.1016/j.compchemeng.2022.107738. DOI: https://doi.org/10.1016/j.compchemeng.2022.107738
[19] N. Pachhala, S. Jothilakshmi, and B. P. Battula, Android malware classification using LSTM model, Revue dIntelligence Artificielle, vol. 36, no. 5, pp. 761767, Dec. 2022, doi: 10.18280/ria.360514. DOI: https://doi.org/10.18280/ria.360514
[20] A. Kitanovski, H. M. Trpcheska, and V. Dimitrova, Detecting malware in Android applications using XGBoost, in Proc. 20th Int. Conf. Informatics Inf. Technol., 2023. [Online]. Available: http://hdl.handle.net/20.500.12188/27385.
[21] A. Taha and O. Barukab, Android malware classification using optimized ensemble learning based on genetic algorithms, Sustainability, vol. 14, no. 21, p. 14406, Nov. 2022, doi: 10.3390/su142114406. DOI: https://doi.org/10.3390/su142114406
[22] S. Y. Yerima and S. Sezer, DroidFusion: A novel multilevel classifier fusion approach for Android malware detection, IEEE Transactions on Cybernetics, vol. 49, no. 2, pp. 453466, Feb. 2019, doi: 10.1109/TCYB.2017.2777960. DOI: https://doi.org/10.1109/TCYB.2017.2777960
[23] G. Tamami, W. A. Triyanto, and S. Muzid, "Sentiment Analysis Mobile JKN Reviews Using SMOTE Based LSTM," IJCCS (Indonesian Journal of Computing and Cybernetics Systems), vol. 19, no. 1, pp. 1324, Jan. 2025, doi: 10.22146/ijccs.101910 DOI: https://doi.org/10.22146/ijccs.101910
[24] E. F. Swana, W. Doorsamy, and P. Bokoro, Tomek link and SMOTE approaches for machine fault classification with an imbalanced dataset, Sensors, vol. 22, no. 9, p. 3246, Jan. 2022, doi: 10.3390/s22093246. DOI: https://doi.org/10.3390/s22093246
[25] A. Khleel and K. Nehz, A novel approach for software defect prediction using CNN and GRU based on SMOTE Tomek method, Journal of Intelligent Information Systems, vol. 60, no. 3, pp. 673707, May 2023, doi: 10.1007/s10844-023-00793-1. DOI: https://doi.org/10.1007/s10844-023-00793-1
[26] E. Baaran, A new brain tumor diagnostic model: Selection of textural feature extraction algorithms and convolution neural network features with optimization algorithms, Computers in Biology and Medicine, vol. 148, p. 105857, Sep. 2022, doi: 10.1016/j.compbiomed.2022.105857. DOI: https://doi.org/10.1016/j.compbiomed.2022.105857
[27] R. Chen, C. Dewi, S. Huang and R. E. Caraka, Selecting critical features for data classification based on machine learning methods, Journal of Big Data, vol. 7, no. 1, Jul. 2020, doi: 10.1186/s40537-020-00327-4. DOI: https://doi.org/10.1186/s40537-020-00327-4
[28] J. Hermo, V. Boln-Canedo, and S. Ladra, Fed-mRMR: A lossless federated feature selection method, Information Sciences, vol. 669, p. 120609, Apr. 2024, doi: 10.1016/j.ins.2024.120609. DOI: https://doi.org/10.1016/j.ins.2024.120609
[29] G. Wang, F. Lauri, and A. H. E. Hassani, Feature selection by mRMR method for heart disease diagnosis, IEEE Access, vol. 10, pp. 100786100796, Jan. 2022, doi: 10.1109/ACCESS.2022.3207492. DOI: https://doi.org/10.1109/ACCESS.2022.3207492
[30] S. Xie, Y. Zhang, D. Lv, X. Chen, J. Lu, and J. Liu, A new improved maximal relevance and minimal redundancy method based on feature subset, J. Supercomput., vol. 79, no. 3, pp. 31573180, Aug. 2022, doi: 10.1007/s11227-022-04763-2. DOI: https://doi.org/10.1007/s11227-022-04763-2
[31] M. Agar, S. Aydin, M. Cakmak, M. Koc, and M. Togacar, Detection of Thymoma Disease Using mRMR Feature Selection and Transformer Models, Diagnostics, vol. 14, no. 19, p. 2169, Sep. 2024, doi: 10.3390/diagnostics14192169. DOI: https://doi.org/10.3390/diagnostics14192169
[32] M. Toaar, B. Ergen, and Z. Cmert, Detection of lung cancer on chest CT images using minimum redundancy maximum relevance feature selection method with convolutional neural networks, Biocybern. Biomed. Eng., Nov. 2019, doi: 10.1016/j.bbe.2019.11.004. DOI: https://doi.org/10.1016/j.bbe.2019.11.004
[33] E. S. Alomari et al., Malware Detection Using Deep Learning and Correlation-Based Feature Selection, Symmetry, vol. 15, no. 1, p. 123, Jan. 2023, doi: 10.3390/sym15010123. DOI: https://doi.org/10.3390/sym15010123
[34] D. C. E. Saputra, Y. Maulana, T. A. Win, R. Phann, and W. Caesarendra, Implementation of Machine Learning and Deep Learning Models Based on Structural MRI for Identification Autism Spectrum Disorder, J. Ilm. Tek. Elektro Komput. Inform., vol. 9, no. 2, pp. 307318, May 2023, doi: 10.26555/jiteki.v9i2.26094. DOI: https://doi.org/10.26555/jiteki.v9i2.26094
[35] M. Schonlau and R. Y. Zou, The random forest algorithm for statistical learning, Stata J., vol. 20, no. 1, pp. 329, Mar. 2020, doi: 10.1177/1536867x20909688. DOI: https://doi.org/10.1177/1536867X20909688
[36] A. Tajali, T. H. Saragih, M. I. Mazdadi, I. Budiman and A. Farmadi, "The Impactness of SMOTE as Imbalance Class Handling for Myocardial Infarction Complication Classification using Machine Learning Approach with Data Imputation and Hyperparameter," Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics, pp. Vol. 6, No. 4, pp. 227-239, 2024, doi: 10.35882/ijeeemi.v6i4.13
[37] S. Talukdar et al., Land-Use Land-Cover Classification by Machine Learning Classifiers for Satellite ObservationsA Review, Remote Sensing, vol. 12, no. 7, p. 1135, Apr. 2020, doi: 10.3390/rs12071135. DOI: https://doi.org/10.3390/rs12071135
[38] T. Chen and C. Guestrin, XGBoost: a Scalable Tree Boosting System, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD 16, vol. 1, no. 1, pp. 785794, Aug. 2016, doi: 10.1145/2939672.2939785. DOI: https://doi.org/10.1145/2939672.2939785
[39] A. Asselman, M. Khaldi, and S. Aammou, Enhancing the prediction of student performance based on the machine learning XGBoost algorithm, Interactive Learning Environments, vol. 31, no. 6, pp. 120, May 2021, doi: 10.1080/10494820.2021.1928235. DOI: https://doi.org/10.1080/10494820.2021.1928235
[40] Y. Tang, Y.-C. Chang, and K. Li, Applications of K-nearest neighbor algorithm in intelligent diagnosis of wind turbine blades damage, Renewable Energy, vol. 212, pp. 855864, Aug. 2023, doi: 10.1016/j.renene.2023.05.087. DOI: https://doi.org/10.1016/j.renene.2023.05.087
[41] Y. Hamed, A. Ibrahim Alzahrani, A. Shafie, Z. Mustaffa, M. Che Ismail, and K. Kok Eng, Two steps hybrid calibration algorithm of support vector regression and K-nearest neighbors, Alexandria Engineering Journal, vol. 59, no. 3, pp. 11811190, Jun. 2020, doi: 10.1016/j.aej.2020.01.033. DOI: https://doi.org/10.1016/j.aej.2020.01.033
[42] B. Du, S. Wang, N. Wang, L. Zhang, D. Tao, and L. Zhang, Hyperspectral signal unmixing based on constrained non-negative matrix factorization approach, Neurocomputing (Amsterdam), vol. 204, pp. 153161, Sep. 2016, doi: 10.1016/j.neucom.2015.10.132. DOI: https://doi.org/10.1016/j.neucom.2015.10.132
[43] H. A. Abu Alfeilat et al., Effects of Distance Measure Choice on K-Nearest Neighbor Classifier Performance: A Review, Big Data, vol. 7, no. 4, pp. 221248, Dec. 2019, doi: 10.1089/big.2018.0175. DOI: https://doi.org/10.1089/big.2018.0175
[44] I. Lee and C. Torpelund-Bruin, Geographic knowledge discovery from Web Map segmentation through generalized Voronoi diagrams, Expert Systems with Applications, vol. 39, no. 10, pp. 93769388, Aug. 2012, doi: 10.1016/j.eswa.2012.02.129. DOI: https://doi.org/10.1016/j.eswa.2012.02.129
[45] P. Cunningham and S. J. Delany, k-Nearest Neighbour Classifiers - A Tutorial, ACM Computing Surveys, vol. 54, no. 6, pp. 125, Jul. 2021, doi: 10.1145/3459665. DOI: https://doi.org/10.1145/3459665
[46] S. Abbaspour, F. Fotouhi, A. Sedaghatbaf, H. Fotouhi, M. Vahabi, and M. Linden, A Comparative Analysis of Hybrid Deep Learning Models for Human Activity Recognition, Sensors, vol. 20, no. 19, p. 5707, Oct. 2020, doi: 10.3390/s20195707. DOI: https://doi.org/10.3390/s20195707
[47] S. Hochreiter and J. Schmidhuber, Long Short-Term Memory, Neural Computation, vol. 9, no. 8, pp. 17351780, Nov. 1997, doi: 10.1162/neco.1997.9.8.1735. DOI: https://doi.org/10.1162/neco.1997.9.8.1735
[48] A. Graves, Generating sequences with recurrent neural networks, arXiv preprint arXiv:1308.0850v5, Jun. 2014, doi: 10.48550/arXiv.1308.0850.
[49] S. Minaee, E. Amini, and A. A. Abdolrashidi, Deep-sentiment: Sentiment analysis using ensemble of CNN and Bi-LSTM models, arXiv preprint arXiv:1904.04206v1, Apr. 2019, doi: 10.48550/arXiv.1904.04206.
[50] W. Fang, Y. Chen, and Q. Xue, Survey on Research of RNN-Based Spatio-Temporal Sequence Prediction Algorithms, Journal on Big Data, vol. 3, no. 3, pp. 97110, 2021, doi: 10.32604/jbd.2021.016993. DOI: https://doi.org/10.32604/jbd.2021.016993
[51] D. Gaur and S. Kumar Dubey, Develompent of Activity Recognition Model using LSTM-RNN Deep Learning Algorithm, Journal of information and organizational sciences, vol. 46, no. 2, pp. 277291, Dec. 2022, doi: 10.31341/jios.46.2.1. DOI: https://doi.org/10.31341/jios.46.2.1
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Muhammad Alif Fadhillah, Setyo Wahyu Saputro, Muliadi Muliadi, Mohammad Reza Faisal, Radityo Adi Nugroho
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
How to Cite
Share
Plum Analytics