Machine Learning-Driven Approaches for Advanced Collaborative Malware Analysis and Detection

DOI

10.2991/978-94-6239-654-8_53How to use a DOI?

Keywords

Machine Learning-Driven Approaches; Collaborative Malware Analysis; Malware Detection; Hybrid Graph-MaIX; Graph neural networks; Transformer Models; URL malware

Abstract

The malware keeps on developing with increasing complexities, and these conventional methods have some challenges. To overcome the challenges of these issues, this research presents a new idea and proposes Hybrid Graph-MaIX, a novel combination of Graph Neural Network and Transformers model designed for advanced collaborative malware analysis and detection. It delves into this approach, explores graph representations concepts for app behavior of application behavior and URL structure jointly, which have the capability to encapsulate and represent the complex relational graphs dependencies among malicious entity units. The transformer updates to improve and enhance contextual understanding and capabilities within learning and empower the model to generalize to various malware families and obfuscation pattern recognition techniques. The proposed framework method will be tested and evaluated on Android apps and URL-based malware datasets, demonstrating its efficacy and applicability as an efficient solution for practical use and showing the effectiveness of the approach in real-world scenarios. By combining the Integrating capabilities of the collaborative intelligence, the proposed system will provide an advanced facility that enables cross-platform and multi-source threat analysis and enhances resilience to emergent attacks. The experimental findings clearly demonstrate that the Experimental results indicate that Hybrid Graph-MaIX achieves an accuracy of the suggested algorithm that exceeds 97.15% outperforming conventional state-of-the-art machine learning and deep learning baselines. This research clearly emphasizes developing scalable and interpretable, highly efficient malware detection through collaborative intelligent capability, which underlines the potential of machine learning collaborative approaches to push state -of-the-art malware detection, yielding a scalable and interpretable high-performance solution for modern cybersecurity ecosystems. The findings will be useful as the results are expected to contribute to the development of next-generation security systems for safeguarding emerging frameworks that protect mobile and web platforms against new environments from emerging threats.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Giragani Nageshwar
AU  - R. Yogesh Rajkumar
PY  - 2026
DA  - 2026/04/24
TI  - Machine Learning-Driven Approaches for Advanced Collaborative Malware Analysis and Detection
BT  - Proceedings of the Global Conference on Sustainable Energy Systems, Smart Electronics and Intelligent Computing (GCSESEIC 2025)
PB  - Atlantis Press
SP  - 666
EP  - 682
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-654-8_53
DO  - 10.2991/978-94-6239-654-8_53
ID  - Nageshwar2026
ER  -