Android Permissions for Malware Detection: A Preliminary Study

• Joner Assolin UNIPAMPA http://orcid.org/0000-0001-8517-6600
• Guilherme Siqueira UNIPAMPA https://orcid.org/0000-0002-8621-0660
• Gustavo Rodrigues UNIPAMPA https://orcid.org/0000-0001-8944-0958
• Diego Kreutz UNIPAMPA https://orcid.org/0000-0003-0830-0238

DOI: https://doi.org/10.5753/sbseg_estendido.2021.17356

Abstract

The large number of static and dynamic features impacts the performance of machine learning-based malware detection systems. To address scalability issues, works such as SigPID try to selectively reduce the number of permissions, one of the most widely used features. We investigate the reproducibility of SigPID and provide a list of the most frequently used permissions by existing solutions. Additionally, we provide an initial implementation and evaluation of SigPID's machine learning methods using a publicly available dataset. Our initial findings suggest that the number of permissions impacts training and execution time, as well as the accuracy of the machine learning methods. However, a slightly higher execution time might be less significant than the accuracy of the methods for detecting malicious applications when users are installing them on their smartphones.

References

Alsoghyer, S. and Almomani, I. (2020). On the effectiveness of application permissions for android ransomware detection. In 2020 6th Conference on Data Science and Machine Learning Applications (CDMA), pages 94–99.

Amidi, A. and Amidi, S. (2020). Machine learning tips and tricks cheatsheet. AYsan, A. I. and sen, S. (2015). Api call and permission based mobile malware detection (in english). In 2015 23nd Signal Processing and Communications Applications Conference (SIU), pages 2400–2403.

Bayazit, E. C., Sahingoz, O. K., and Dogan, B. (2020). Malware detection in android In 2020 International systems with traditional machine learning models: a survey. Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), pages 1–8. IEEE.

Chakkaravarthy, S. S., Sangeetha, D., and Vaidehi, V. (2019). A survey on malware analysis and mitigation techniques. Computer Science Review, 32:1–23.

Gyam, N. K. and Owusu, E. (2018). Survey of mobile malware analysis, detection techniques and tool. In 2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON), pages 1101–1107. IEEE.

Idrees, F., Rajarajan, M., Conti, M., Chen, T. M., and Rahulamathavan, Y. (2017). Pindroid: A novel android malware detection system using ensemble learning methods. Computers & Security, 68:36–46.

James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013). An introduction to statistical learning, volume 112. Springer.

Li, J., Sun, L., Yan, Q., Li, Z., Srisa-an, W., and Ye, H. (2018). Signicant permission identication for machine-learning-based android malware detection. IEEE Transactions on Industrial Informatics, 14(7):3216–3225.

Lopez, C. C. U. and Cadavid, A. N. (2016). Machine learning classiers for android malware analysis. In 2016 IEEE Colombian Conference on Communications and Computing (COLCOM), pages 1–6.

Martín, A., Lara-Cabrera, R., and Camacho, D. (2019). Android malware detection through hybrid features fusion and ensemble classiers: The andropytool framework and the omnidroid dataset. Information Fusion, 52:128–142.

Peiravian, N. and Zhu, X. (2013). Machine learning for android malware detection using permission and api calls. In 2013 IEEE 25th international conference on tools with articial intelligence, pages 300–305. IEEE.

Sangal, A. and Verma, H. K. (2020). A static feature selection-based android malware In 2020 International Conference on detection using machine learning techniques. Smart Electronics and Communication (ICOSEC), pages 48–51.

Sharma, T. and Rattan, D. (2021). Malicious application detection in android-a systematic literature review. Computer Science Review, 40:100373.

Soares, T., Siqueira, G., Barcellos, L., Sayyed, R., Vargas, L., Rodrigues, G., Assolin, J., Pontes, J., and Kreutz, D. (2021). Detecção de malwares android: datasets e reprodutibilidade. https://arxiv.kreutz.xyz/mh21_reprodutibilidade.pdf.

Sun, L., Li, Z., Yan, Q., Srisa-an, W., and Pan, Y. (2016). Sigpid: signicant permission identication for android malware detection. In 2016 11th international conference on malicious and unwanted software (MALWARE), pages 1–8. IEEE.

Tam, K., Feizollah, A., Anuar, N. B., Salleh, R., and Cavallaro, L. (2017). The evolution of android malware and android analysis techniques. ACM Computing Surveys (CSUR), 49(4):1–41.

Wang, W., Wang, X., Feng, D., Liu, J., Han, Z., and Zhang, X. (2014). Exploring permission-induced risk in android applications for malicious application detection. IEEE Transactions on Information Forensics and Security, 9(11):1869–1882.

Wu, Q., Zhu, X., and Liu, B. (2021). A survey of android malware static detection technology based on machine learning. Mobile Information Systems, 2021.

Yildiz, O. and Dogru, I. A. (2019). Permission-based android malware detection system using feature selection with genetic algorithm. International Journal of Software Engineering and Knowledge Engineering, 29(02):245–262.