Android Malware Detection Using Machine Learning
Download| Volume 5 Issue 2 2024 | |
|---|---|
| Author(s): |
Rageshwari Haryani SZABIST University Karachi, Pakistan, rageshwariharyani1997@gmail.com Muhammad Raza* SZABIST University Gharo Campus, Pakistan, dr.raza@ghr.szabist.edu.pk Zahoor Hussain Iqra University Karachi, Pakistan, zahoor.hussain@iqra.edu.pk Sabih Hida Tahir SZABIST University Karachi, Pakistan, sabihhida@hotmail.com Almina Sehrish SZABIST University Karachi, Pakistan, Alminasehrish88@gmail.com |
| Abstract | Android malware is becoming a severe problem since it can take your identity, slow your phone, and even take your money. As a consequence of this, researchers are employing machine learning to help develop a technique to automatically block such applications. In this research, we attempted to discover the best approach for the classification of machine learning algorithms in identifying Android malware. Random Forest, Decision Trees, Gradient Boosting, and powerful deep learning models like LSTM, CNN-LSTM, and LSTM-GRU were used in the experiment. The analysis proved that tree-based methods were more accurate and efficient among all the models including XGBoost and Gradient Boosting. But deep learning models were doing a very good job in recognizing many-layered patterns, and that was when it became clear why: they were very compute-intensive, and not very suitable as real-time phone apps. This research also demonstrates the use and advantages of tree-based models to discover Android malware, particularly on small and constrained platforms. This is a great advancement in endeavoring to safeguard Android users from modern scourges. |
| Keywords | augmented reality, virtual reality, hand segmentation, hand gesture recognition, text-based input, immersive interfaces, CNN |
| Year | 2024 |
| Volume | 5 |
| Issue | 2 |
| Type | Research paper, manuscript, article |
| Recognized by | Higher Education Commission of Pakistan, HEC | Category | Journal Name | ILMA Journal of Technology & Software Management | Publisher Name | ILMA University | Jel Classification | -- | DOI | - | ISSN no (E, Electronic) | 2790-590X | ISSN no (P, Print) | 2709-2240 | Country | Pakistan | City | Karachi | Institution Type | University | Journal Type | Open Access | Manuscript Processing | Blind Peer Reviewed | Format | Paper Link | https://ijtsm.ilmauniversity.edu.pk/arc/Vol5/i2/pdf5.pdf | Page | 41-54 |