Android Security: Malware Detection with Convolutional Neural Network and Feature Analysis
DOI:
https://doi.org/10.62205/mjgcs.v1i1.7Keywords:
Malware, Android, PCA, CNNAbstract
Android is a mobile operating system based on a modified version of the Linux kernel and other open-source tools. Due to its system efficiency and the multitude of features it offers to users, the Android operating system has taken a leading position in the technology market and often attracts the attention of cybercriminals. As malware continues to evolve, traditional methods for detecting Android malware, such as signature-based approaches, may not be sufficient to detect the latest malware threats. Therefore, this research proposes a deep learning algorithm, specifically Convolutional Neural Network (CNN) and Component Analysis (PCA), for feature extraction to enhance the accuracy of Android malware detection. The dataset used in this study is the CICAndMal2017 dataset. Testing results are evaluated using three parameters: accuracy, precision, and recall. Experimental results indicate that our deep learning approach outperforms many other methods with an accuracy of 91%.
References
M. K. Alzaylaee, S. Y. Yerima, and S. Sezer, “DL-Droid: Deep learning based android malware detection using real devices,” Comput. Secur., vol. 89, p. 101663, 2020, doi: 10.1016/j.cose.2019.101663.
X. Wang and C. Li, “Android malware detection through machine learning on kernel task structures,” Neurocomputing, vol. 435, pp. 126–150, 2021, doi: 10.1016/j.neucom.2020.12.088.
S. Lee et al., “LARGen: Automatic Signature Generation for Malwares Using Latent Dirichlet Allocation,” IEEE Trans. Dependable Secur. Comput., vol. 15, no. 5, pp. 771–783, 2018, doi: 10.1109/TDSC.2016.2609907.
A. Souri and R. Hosseini, “A state-of-the-art survey of malware detection approaches using data mining techniques,” Human-centric Comput. Inf. Sci., vol. 8, no. 1, 2018, doi: 10.1186/s13673-018-0125-x.
H. M. Deylami, R. C. Muniyandi, I. T. Ardekani, and A. Sarrafzadeh, “Taxonomy of malware detection techniques: A systematic literature review,” 2016 14th Annu. Conf. Privacy, Secur. Trust. PST 2016, pp. 629–636, 2016, doi: 10.1109/PST.2016.7906998.
Y. Wanli Sitorus, P. Sukarno, dan S. Mandala, “Analisis Deteksi Malware Android menggunakan metode Support Vector Machine & Random Forest,” e-Proceeding of Engineering, vol. 8, no. 6, hlm. 12500, 2021.
R. B. Hadiprakoso, N. Qomariasih, dan R. N. Yasa, “IDENTIFIKASI MALWARE ANDROID MENGGUNAKAN PENDEKATAN ANALISIS HIBRID DENGAN DEEP LEARNING,” Jurnal Teknologi Informasi Universitas Lambung Mangkurat, vol. 6, no. 2, hlm. 77–84, 2021.
O. N. Elayan dan A. M. Mustafa, “Android malware detection using deep learning,” dalam Procedia Computer Science, Elsevier B.V., 2021, hlm. 847–852. doi: 10.1016/j.procs.2021.03.106.
Sharipuddin, E. A. Winanto, Z. Z. Mohtar, Kurniabudi, I. S. Wijaya, and D. Sandra, “Improvement detection system on complex network using hybrid deep belief network and selection features,” Indones. J. Electr. Eng. Comput. Sci., vol. 31, no. 1, pp. 470–479, 2023, doi: 10.11591/ijeecs.v31.i1.pp470-479.
S. Sharipuddin et al., “Enhanced Deep Learning Intrusion Detection in IoT Heterogeneous Network with Feature Extraction,” Int. J. Electr. Eng. Informatics, vol. 9, no. 3, pp. 747–755, 2021, doi: 10.52549/ijeei.v9i3.3134.
A. H. Lashkari, A. F. A. Kadir, L. Taheri, and A. A. Ghorbani, “Toward Developing a Systematic Approach to Generate Benchmark Android Malware Datasets and Classification,” Proc. - Int. Carnahan Conf. Secur. Technol., vol. 2018-October, no. Cic, pp. 1–7, 2018, doi: 10.1109/CCST.2018.8585560.
Downloads
Published
Issue
Section
License
Copyright (c) 2023 sharipuddin, Rafi Septiandi Putra, M. Farhan Aulia, Sayid Achmad Maulana, Pareza Alam Jusia
This work is licensed under a Creative Commons Attribution 4.0 International License.
