Klasifikasi Malware Android Dengan Menggunakan Metode XGBoost Algoritma
Article Sidebar
Main Article Content
Abstract
Android, sistem operasi yang dikembangkan oleh Google, mendominasi pasar global dengan pangsa sebesar 71,8% pada akhir tahun 2023. Meskipun keberhasilan ini didorong oleh sifat open-source dan berbagai aplikasi di Google Play Store, Android juga menjadi target utama bagi serangan malware, dengan 97% dari semua serangan malware pada tahun 2022 ditujukan pada perangkat Android. Malware juga kian waktu terus mengalami peningkatan yang menjadikannya semakin sulit untuk dideteksi. Maka dari itu diperlukan metode deteksi yang andal. Pada bidang IT saat ini, machine learning telah menunjukkan hasil yang cukup efisien dalam mendeteksi malware. Penulis mengusulkan metode Algoritma XGBoost sebagai pendekatan klasifikasi malware Android. Dalam penelitian ini, dilakukan penerapan teknik Feature Selection, yaitu Recursive Feature Elimination (RFE) dan Multicollinearity Removal (MR), untuk mengurangi dimensi data dan meningkatkan performa model. Pengujian dilakukan dengan membandingkan kinerja model XGBoost sebelum dan sesudah penerapan Feature Selection. Hasil evaluasi menggunakan classification report dan confusion matrix menunjukkan bahwa model XGBoost yang menerapkan Feature Selection berhasil mencapai Validation Accuracy sebesar 98%, Detection Accuracy sebesar 98%, Precision sebesar 98%, Recall sebesar 98%, dan F1-Score sebesar 98%. Model tanpa Feature Selection hanya mencapai nilai 97% pada metrik yang sama.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
“20 Android Statistics For 2024 (Market Share & Users).” Accessed: Jul. 19, 2024. [Online]. Available: https://www.demandsage.com/android-statistics/
“Android Statistics 2024 - By Market Share, Useres and Revenue.” Accessed: Jul. 19, 2024. [Online]. Available: https://www.enterpriseappstoday.com/stats/android-statistics.html#google_vignette
“Attacks on mobile devices significantly increase in 2023 | Kaspersky.” Accessed: Jul. 19, 2024. [Online]. Available: https://www.kaspersky.com/about/press-releases/2024_attacks-on-mobile-devices-significantly-increase-in-2023
“Statistik malware Android dan perangkat lunak yang tidak diinginkan untuk Q1 2024 | Securelist.” Accessed: Aug. 04, 2024. [Online]. Available: https://securelist.com/it-threat-evolution-q1-2024-mobile-statistics/112750/
Y. Wanli Sitorus, P. Sukarno, S. Mandala, F. Informatika, and U. Telkom, “Analisis Deteksi Malware Android menggunakan metode Support Vector Machine & Random Forest,” e-Proceeding Eng., vol. 8, no. 6, pp. 12500–12518, 2021.
R. B. Hadiprakoso, W. R. Aditya, and F. N. Pramitha, “Analisis Statis Deteksi Malware Android Menggunakan Algoritma Supervised Machine Learning,” Cyber Secur. dan Forensik Digit., vol. 5, no. 1, pp. 1–5, 2022, doi: 10.14421/csecurity.2022.5.1.3116.
F. M. Darus, N. A. Ahmad, and A. F. M. Ariffin, “Android malware classification using XGBoost on data image pattern,” Proc. - 2019 IEEE Int. Conf. Internet Things Intell. Syst. IoTaIS 2019, pp. 118–122, 2019, doi: 10.1109/IoTaIS47347.2019.8980412.
J. Wang, B. Li, and Y. Zeng, “XGBoost-Based Android Malware Detection,” pp. 268–272, 2017, doi: 10.1109/CIS.2017.00065.
M. E. N. Et. al., “Malware Classification Using Xgboost With Vote Based Backward Feature Elimination Technique,” Turkish J. Comput. Math. Educ., vol. 12, no. 10, pp. 5915–5923, 2021, doi: 10.17762/turcomat.v12i10.5412.
J. Palša et al., “MLMD—A Malware-Detecting Antivirus Tool Based on the XGBoost Machine Learning Algorithm,” Appl. Sci., vol. 12, no. 13, 2022, doi: 10.3390/app12136672.
A. Meena, R. Karishma, B. Gayathri, and K. B. Hemapriya, “Android Malware Detection Using Extreme Gradient Boosting Algorithm,” vol. 9, no. 4, 2023.
L. Suhuan and H. Xiaojun, “Android malware detection based on logistic regression and XGBoost,” Proc. IEEE Int. Conf. Softw. Eng. Serv. Sci. ICSESS, vol. 2019-Octob, pp. 528–532, 2019, doi: 10.1109/ICSESS47205.2019.9040851.
“Android Architecture: Application Layers, Framework, Component.” Accessed: Aug. 31, 2024. [Online]. Available: https://www.guru99.com/android-architecture.html
“Android Architecture: A Comprehensive Overview Its Layers and Functions – Techporfit.” Accessed: Aug. 31, 2024. [Online]. Available: https://techporfit.com/android-architecture/
O. Aslan and R. Samet, “A Comprehensive Review on Malware Detection Approaches,” IEEE Access, vol. 8, pp. 6249–6271, 2020, doi: 10.1109/ACCESS.2019.2963724.
K. Liu, S. Xu, G. Xu, M. Zhang, D. Sun, and H. Liu, “A Review of Android Malware Detection Approaches Based on Machine Learning,” IEEE Access, vol. 8, pp. 124579–124607, 2020, doi: 10.1109/ACCESS.2020.3006143.
E. J. Sudarman and S. Budi, “Pengembangan Model Kecerdasan Mesin Extreme Gradient Boosting untuk Prediksi Keberhasilan Studi Mahasiswa,” J. Strateg., vol. 5, no. 2, pp. 297–314, 2023.
A. Mathur, L. M. Podila, K. Kulkarni, Q. Niyaz, and A. Y. Javaid, “NATICUSdroid: A malware detection framework for Android using native and custom permissions,” J. Inf. Secur. Appl., vol. 58, p. 102696, May 2021, doi: 10.1016/J.JISA.2020.102696.
“Manifest.permission | Android Developers.” Accessed: Jul. 21, 2024. [Online]. Available: https://developer.android.com/reference/android/Manifest.permission
“Data Wrangling for Machine Learning | StreamSets.” Accessed: Jul. 21, 2024. [Online]. Available: https://www.softwareag.com/en_corporate/blog/streamsets/data-wrangling-for-machine-learning.html
J. A. Ramírez-Hernández and E. Fernandez, “Enhanced recursive feature elimination,” Proc. - 6th Int. Conf. Mach. Learn. Appl. ICMLA 2007, pp. 330–335, 2007, doi: 10.1109/ICMLA.2007.35.
A. N. Iman, M. T. Avon Budiyono, S.T., and M. T. Ahmad Almaarif, S.Kom., “Analisis Malware Pada Sistem Operasi Android Menggunakan Permission-Based Malware Analysis in Android Operation System Using Permission-Based,” Angew. Chemie Int. Ed. 6(11), 951–952., vol. 6, no. Mi, pp. 5–24, 1967.