Malware-SeqGuard: An Approach Utilizing LSTM and GRU for Effective Detection of Evolving Malware in Android Environments
Malware detection is crucial for safeguarding devices and networks from malicious software that can compromise sensitive information, disrupt operations, and lead to financial losses. By identifying and neutralizing threats early effective malware detection helps maintain the integrity confidentiali...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11069258/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Malware detection is crucial for safeguarding devices and networks from malicious software that can compromise sensitive information, disrupt operations, and lead to financial losses. By identifying and neutralizing threats early effective malware detection helps maintain the integrity confidentiality and availability of critical systems and data. In this study, we introduce a state-of-the-art scheme for Android malware detection that combines the strengths of Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks. These advanced deep learning architectures are particularly adept at capturing sequential dependencies within data making them well-suited for analyzing complex time-series information, such as user behaviour patterns system logs and network traffic. By leveraging the complementary capabilities of both LSTM and GRU models can effectively dissect intricate and dynamic data to uncover malicious activities that often evade conventional detection methods. This innovative approach not only enhances the model’s ability to identify known malware but also empowers it to adapt to emerging threats by continuously learning from both historical and real-time behavioural data. As malware evolves in sophistication, our model improves detection accuracy and response times, ensuring robust defences against new attack vectors in Android environments. The findings from our research underscore the potential of combining different neural network architectures to create more resilient cybersecurity solutions, paving the way for more effective malware detection strategies in an increasingly complex digital landscape. By addressing the limitations of traditional methods, our proposed model represents a significant advancement in safeguarding Android systems from the ever-growing range of malware threats. |
|---|---|
| ISSN: | 2169-3536 |