Malware Detection for Android Systems using Neural Networks
DOI:
https://doi.org/10.59992/IJCI.2025.v4n3p2Keywords:
Malware Detection, Android Systems, Deep Learning Methods, Drebin Dataset, MH-100K DatasetAbstract
The proliferation of Android malware poses an ever-growing menace to billions of mobile users worldwide. Detection systems are updated constantly to address these threats. Nevertheless, a counteraction arises in the form of evasion attacks, where an opponent modifies malicious samples in a way that causes them to be incorrectly classified as benign. In this paper, the proposed method aimed to investigate the signs of malware on Android devices, and to develop a malware detection model for Android systems based on the Drebin and the MH-100K datasets. We used each of the LSTM, MLP, and RNNs for reducing and detecting the threats and malware to enhance security over the Android systems. Each algorithm works separately and calls the sub-algorithms in the feature selection (PCA, and CFS). We used several scenarios for testing the performance of each algorithm according to the number of attributes in both datasets and the number of epochs for each algorithm. The experiment results showed the preference of results for the MH-100K dataset compared to the Drebin dataset. On the other hand, the results showed that the accuracy for the LSTM algorithm reached (98.31%) and outperformed both the MLP and the RNN algorithms for malware detection for both datasets.
References
1. B. Tahtaci and B. Canbay, “Android Malware Detection Using Machine Learning,” Proc. - 2020 Innov. Intell. Syst. Appl. Conf. ASYU 2020, 2020, doi: 10.1109/ASYU50717.2020.9259834.
2. H. Papadopoulos, N. Georgiou, C. Eliades, and A. Konstantinidis, “Android malware detection with unbiased confidence guarantees,” Neurocomputing, vol. 280, pp. 3–12, 2018, doi: 10.1016/j.neucom.2017.08.072.
3. H. Bragança, V. Rocha, L. Barcellos, E. Souto, D. Kreutz, and E. Feitosa, “Android malware detection with MH-100K: An innovative dataset for advanced research,” Data Br., vol. 51, 2023, doi: 10.1016/j.dib.2023.109750.
4. M. Altaİy, İ. Yildiz, and B. Uçan, “MALWARE DETECTION USING DEEP LEARNING ALGORITHMS,” vol. 7, no. 1, pp. 11–26, 2023.
5. A. Hota and P. Irolla, “Deep Neural Networks for Android Malware Detection,” Int. Conf. Inf. Syst. Secure. Priv., no. Icissp, pp. 657–663, 2019, doi 10.5220/0007617606570663.
6. E. C. Bayazit, O. K. Sahingoz, and B. Dogan, “Neural Network Based Android Malware Detection with Different IP Coding Methods,” HORA 2021 - 3rd Int. Congr. Human-Computer Interact. Optim. Robot. Appl. Proc., no. November 2020, 2021, doi: 10.1109/HORA52670.2021.9461302.
7. H. Rathore, S. K. Sahay, P. Nikam, and M. Sewak, “Robust Android Malware Detection System Against Adversarial Attacks Using Q-Learning,” Inf. Syst. Front., vol. 23, no. 4, pp. 867–882, 2021, doi: 10.1007/s10796-020-10083-8.
8. R. Kumar, W. Wang, J. Kumar, Zakria, T. Yang, and W. Ali, “Collective Intelligence: Decentralized Learning for Android Malware Detection in IoT with Blockchain,” no. i, pp. 1–15, 2021, [Online]. Available: http://arxiv.org/abs/2102.13376.
9. T. Sun, W. Pian, N. Daoudi, K. Allix, T. F. Bissyandé, and J. Klein, “LaFiCMIL: Rethinking Large File Classification from the Perspective of Correlated Multiple Instance Learning,” no. Mil, 2023, [Online]. Available: http://arxiv.org/abs/2308.01413.
10. H. Rathore, S. K. Sahay, S. Thukral, and M. Sewak, “Detection of Malicious Android Applications: Classical Machine Learning vs. Deep Neural Network Integrated with Clustering,” Lect. Notes Inst. Comput. Sci. Soc. Telecommun. Eng. LNICST, vol. 355, pp. 109–128, 2021, doi: 10.1007/978-3-030-68737-3_7.
11. F. Taher, O. Al Fandi, M. Al Kfairy, H. Al Hamadi, and S. Alrabaee, “A Proposed Artificial Intelligence Model for Android-Malware Detection,” Informatics, vol. 10, no. 3, 2023, doi: 10.3390/informatics10030067.
12. H. Rathore, S. K. Sahay, R. Rajvanshi, and M. Sewak, “Identification of Significant Permissions for Efficient Android Malware Detection,” Lect. Notes Inst. Comput. Sci. Soc. Telecommun. Eng. LNICST, vol. 355, pp. 33–52, 2021, doi: 10.1007/978-3-030-68737-3_3.
13. A. Muzaffar, H. R. Hassen, H. Zantout, and M. A. Lones, “A Comprehensive Investigation of Feature and Model Importance in Android Malware Detection,” pp. 1–18, 2023, [Online]. Available: http://arxiv.org/abs/2301.12778.
14. H. Bostani, Z. Zhao, Z. Liu, and V. Moonsamy, “Level Up with RealAEs: Leveraging Domain Constraints in Feature Space to Strengthen Robustness of Android Malware Detection,” no. Ml, 2022, [Online]. Available: http://arxiv.org/abs/2205.15128.
15. W. W. Lo, S. Layeghy, M. Sarhan, M. Gallagher, and M. Portmann, “Graph Neural Network-based Android Malware Classification with Jumping Knowledge,” 5th IEEE Conf. Dependable Secur. Comput. DSC 2022 SECSOC 2022 Work. PASS4IoT 2022 Work. SICSA Int. Pap. Compet. Cybersecurity, no. June 2022, doi: 10.1109/DSC54232.2022.9888878.
16. B. Molina-coronado, A. Ruggia, U. Mori, A. Merlo, A. Mendiburu, and J. Miguel-alonso, “Light up that Droid ! On the Effectiveness of Static Analysis Features against App Obfuscation for Android Malware Detection,” pp. 1–16.
17. M. K. Alzaylaee, S. Y. Yerima, and S. Sezer, “DL-Droid: Deep learning based android malware detection using real devices,” Comput. Secur., vol. 89, 2020, doi 10.1016/j.cose.2019.101663.
18. Daniel Arp, M. Spreitzenbarth, M. Hubner, H. Gascon, and K. Rieck, “DREBIN: Effective and Explainable Detection of Android Malware in Your Pocket,” J. Jpn. Stud., vol. 36, no. 1, pp. 165–169, 2014, doi: 10.1353/jjs.0.0130.
19. M. S. Saleem, J. Mišić, and V. B. Mišić, “Android Malware Detection using Feature Ranking of Permissions,” 2022, [Online]. Available: http://arxiv.org/abs/2201.08468.
20. Z. Yang, F. Deng, and L. Han, “Flexible Android Malware Detection Model based on Generative Adversarial Networks with Code Tensor,” Proc. - 2022 Int. Conf. Cyber-Enabled Distrib. Comput. Knowl. Discov. CyberC 2022, pp. 19–28, 2022, doi: 10.1109/CyberC55534.2022.00015.
21. M. Al-Hawawreh, A. Aljuhani, and Y. Jararweh, “Chatgpt for cybersecurity: practical applications, challenges, and future directions,” Cluster Comput., vol. 26, no. 6, pp. 3421–3436, 2023, doi: 10.1007/s10586-023-04124-5.
22. S. Suresh, F. Di Troia, K. Potika, and M. Stamp, “An analysis of Android adware,” J. Comput. Virol. Hacking Tech., vol. 15, no. 3, pp. 147–160, 2019, doi: 10.1007/s11416-018-0328-8.
23. M. Odusami, O. Abayomi-Alli, S. Misra, O. Shobayo, R. Damasevicius, and R. Maskeliunas, Android Malware Detection: A Survey, vol. 942. Springer International Publishing, 2018.
24. M. A. Omer et al., “Efficiency of Malware Detection in Android System: A Survey,” Asian J. Res. Comput. Sci., no. April, pp. 59–69, 2021, doi: 10.9734/ajrcos/2021/v7i430189.
25. H. Babbar, S. Rani, D. K. Sah, S. A. AlQahtani, and A. Kashif Bashir, “Detection of Android Malware in the Internet of Things through the K-Nearest Neighbor Algorithm,” Sensors, vol. 23, no. 16, pp. 1–17, 2023, doi: 10.3390/s23167256.
26. H. Berger, C. Hajaj, E. Mariconti, and A. Dvir, “MaMaDroid2.0 -- The Holes of Control Flow Graphs,” 2022, [Online]. Available: http://arxiv.org/abs/2202.13922.
27. N. Daoudi, K. Allix, T. F. Bissyandé, and J. Klein, “A two-steps approach to improve the performance of Android malware detectors,” 2022, [Online]. Available: http://arxiv.org/abs/2205.08265.
28. S. I. Imtiaz, S. ur Rehman, A. R. Javed, Z. Jalil, X. Liu, and W. S. Alnumay, “DeepAMD: Detection and identification of Android malware using high-efficient Deep Artificial Neural Network,” Futur. Gener. Comput. Syst., vol. 115, pp. 844–856, 2021, doi: 10.1016/j.future.2020.10.008.
29. Janke, J., Castelli, M., & Popovič, A. (2019). Analysis of the proficiency of fully connected neural networks in the process of classifying digital images: Benchmark of different classification algorithms on high-level image features from convolutional layers. Expert Systems with Applications, 135, 12–38. https://doi.org/10.1016/j.eswa.2019.05.058.
30. Gumbarević, S., Milovanović, B., Gaši, M., & Bagarić, M. (2020). Application of Multilayer Perceptron Method on Heat Flow Meter Results for Reducing the Measurement Time. 29. https://doi.org/10.3390/ecsa-7-08272.
31. Al-Saif, A. M., Abdel-Sattar, M., Aboukarima, A. M., & Eshra, D. H. (2021). Application of a multilayer perceptron artificial neural network for identification of peach cultivars based on physical characteristics. PeerJ, 9, 1–22. https://doi.org/10.7717/peerj.11529.
32. Saha, S., Paul, G. C., Pradhan, B., Abdul Maulud, K. N., & Alamri, A. M. (2021). Integrating multilayer perceptron neural nets with hybrid ensemble classifiers for deforestation probability assessment in Eastern India. Geomatics, Natural Hazards and Risk, 12(1), 29–62. https://doi.org/10.1080/19475705.2020.1860139.
33. Ibrahim, M., & Elhafiz, R. (2023). Modeling an intrusion detection using recurrent neural networks. Journal of Engineering Research, 11(1), 100013. https://doi.org/10.1016/j.jer.2023.100013.
34. Rahman, S. M., Pawar, S., San, O., Rasheed, A., & Iliescu, T. (2019). Nonintrusive reduced order modeling framework for quasigeostrophic turbulence. Physical Review E, 100(5). https://doi.org/10.1103/PhysRevE.100.053306.
