Analysis and Identification of Malicious Mobile Applications Using Machines Learning

Year : 2025 | Volume : 12 | Issue : 02 | Page : 17 24
    By

    Kala R.,

  • Alagu Lakshmi L.,

  • Aswathi U.,

  • Libi Bharani T.,

  • Sudharshana V.,

  1. Associate Professor, Department of Computer Science and Engineering, Karpagam College of Engineering, Coimbatore, Tamil Nadu, India
  2. UG Scholar, Department of Computer Science and Engineering, Karpagam College of Engineering, Coimbatore, Tamil Nadu, India
  3. UG Scholar, Department of Computer Science and Engineering, Karpagam College of Engineering, Coimbatore, Tamil Nadu, India
  4. UG Scholar, Department of Computer Science and Engineering, Karpagam College of Engineering, Coimbatore, Tamil Nadu, India
  5. UG Scholar, Department of Computer Science and Engineering, Karpagam College of Engineering, Coimbatore, Tamil Nadu, India

Abstract

Over the past few years, malware attacks on the Android platform have surged, posing significant risks to users’ financial security, personal information, and device integrity. In the first half of 2019 alone, approximately 25 million smartphones were infected, highlighting the severity of these threats. The model ranks manifest features based on their frequency in normal and malicious apps, identifying key components that distinguish benign from malicious applications. To improve detection accuracy, redundant and unnecessary features are removed through support thresholds, and a novel algorithm is proposed that uses these ranked features in combination with machine learning classifiers, such as Multilayer Perceptron, to achieve a detection accuracy of 92.26% with just 36 manifest components. Additionally, the study explores the challenges in mobile malware detection and compares deep learning techniques with traditional machine learning approaches. It emphasizes the importance of diverse training datasets and discusses methods such as differential privacy, homomorphic encryption, and federated learning to enhance the detection of new malware. The study also highlights the shortcomings of traditional signature-based and heuristic methods, proposing an advanced framework that combines static and dynamic analysis of mobile applications using machine learning techniques. By evaluating classification algorithms like Multilayer Perceptron, Support Vector Machines, and Deep Neural Networks, the study demonstrates that machine learning-based methods significantly outperform conventional approaches in detecting previously unseen malicious apps.

Keywords: Mobile malware, Android platform, malicious applications, machine learning, deep learning

[This article belongs to Journal of Microcontroller Engineering and Applications ]

How to cite this article:
Kala R., Alagu Lakshmi L., Aswathi U., Libi Bharani T., Sudharshana V.. Analysis and Identification of Malicious Mobile Applications Using Machines Learning. Journal of Microcontroller Engineering and Applications. 2025; 12(02):17-24.
How to cite this URL:
Kala R., Alagu Lakshmi L., Aswathi U., Libi Bharani T., Sudharshana V.. Analysis and Identification of Malicious Mobile Applications Using Machines Learning. Journal of Microcontroller Engineering and Applications. 2025; 12(02):17-24. Available from: https://journals.stmjournals.com/jomea/article=2025/view=215270


References

1. Liu X, Wagner D, Egelman S. Detecting phone theft using machine learning. In Proceedings of the 1st International Conference on Information Science and Systems. 2018 Apr 27; 30–36.
2. Chell S, Chakare S, Sohan P, Sandosh S. Real-Time Threat Detection and Mitigation in Web API Development. In 2024 IEEE International Conference on Electrical Electronics and Computing Technologies (ICEECT). 2024 Aug 29; 1: 1–9.
3. Taha A, Osman AH, Baguda YS. An Intelligent Technique for Android Malware Identification Using Fuzzy Rank-Based Fusion. Technologies. 2025 Jan 23; 13(2): 45.
4. Meijin L, Zhiyang F, Junfeng W, Luyu C, Qi Z, Tao Y, Yinwei W, Jiaxuan G. A systematic overview of android malware detection. Appl Artif Intell. 2022 Dec 31; 36(1): 2007327.
5. Rains T. Cybersecurity Threats, Malware Trends, and Strategies: Discover Risk Mitigation Strategies for Modern Threats to Your Organization. Birmingham: Packt Publishing Ltd.; 2023.
6. Chen S, Lang B, Liu H, Chen Y, Song Y. Android malware detection method based on graph attention networks and deep fusion of multimodal features. Expert Syst Appl. 2024 Mar 1; 237: 121617.
7. Alamro H, Mtouaa W, Aljameel S, Salama AS, Hamza MA, Othman AY. Automated android malware detection using optimal ensemble learning approach for cybersecurity. IEEE Access. 2023 Jul 11; 11: 72509–17.
8. Zhu HJ, Gu W, Wang LM, Xu ZC, Sheng VS. Android malware detection based on multi-head squeeze-and-excitation residual network. Expert Syst Appl. 2023 Feb 1; 212: 118705.
9. Sun H, Xu G, Wu Z, Quan R. Android malware detection based on feature selection and weight measurement. Intell Autom Soft Comput. 2022 Jan 1; 33(1): 585–600.
10. Manzano C, Meneses C, Leger P, Fukuda H. An empirical evaluation of supervised learning methods for network malware identification based on feature selection. Complexity. 2022; 2022(1):6760920.
11. Shatnawi AS, Jaradat A, Yaseen TB, Taqieddin E, Al-Ayyoub M, Mustafa D. An android malware detection leveraging machine learning. Wirel Commun Mob Comput. 2022; 2022(1): 1830201.
12. Kim YK, Lee JJ, Go MH, Kang HY, Lee K. A systematic overview of the machine learning methods for mobile malware detection. Secur Commun Netw. 2022; 2022(1): 8621083.
13. ’ Y Q. R :neural network. Procedia Comput Sci. 2021 Jan 1; 184: 841–6.
14. Abd El-Kareem M, Elshenawy A, Elrfaey F. Mail spam detection using stacking classification. J Al-Azhar Univ Eng Sect. 2017 Oct 1; 12(45): 1242–55.
15. Adnan M, Imam MO, Javed MF, Murtza I. Improving spam email classification accuracy using ensemble techniques: a stacking approach. Int J Inf Secur. 2024;23:505–17. DOI: 10.1007/s10207- 023-00756-1.

16. Al Ali M, Svetinovic D, Aung Z, Lukman S. Malware detection in android mobile platform using machine learning algorithms. In 2017 IEEE International Conference on Infocom Technologies and Unmanned Systems (Trends and Future Directions) (ICTUS). 2017 Dec 18; 763–768.
17. Naway A, Li Y. Using deep neural network for Android malware detection. arXiv preprintarXiv:1904.00736. 2019 Jan 16.
18. Wang W, Gao Z, Zhao M, Li Y, Liu J, Zhang X. Droid Ensemble: Detecting Android malicious applications with ensemble of string and structural static features. IEEE Access. 2018 May 11; 6:31798–807.
19. Chen Z, Yan Q, Han H, Wang S, Peng L, Wang L, Yang B. Machine learning based mobile malware detection using highly imbalanced network traffic. Inf Sci. 2018 Apr 1; 433: 346–64.

Regular Issue Subscription Review Article
Volume 12
Issue 02
Received 26/03/2025
Accepted 17/04/2025
Published 12/05/2025
Publication Time 47 Days
75


My IP

PlumX Metrics