Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{173271,
        author = {Atharva Ghare and Shubham Kumar and Vishwatej Khot and Sagar Bhat and Reshma Kapadi},
        title = {Multi-Class Malware Detection using modified GNN and  Explainable AI},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {9},
        pages = {2674-2680},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=173271},
        abstract = {As malware becomes increasingly sophisticated, traditional detection techniques, such as signature-based systems, face challenges in effectively identifying novel and polymorphic threats. This research introduces a multi-class malware detection framework utilizing a modified Graph Neural Network (GNN) architecture. By converting bytecode and assembly (ASM) files into image representations, the proposed method enhances feature extraction and improves malware characterization. The method utilizes Graph Neural Networks (GNNs) to capture relationships within the data, allowing for a more flexible and resilient detection system. Additionally, Explainable AI (XAI) techniques, such as Grad-CAM, are integrated to improve transparency by offering visual explanations of the model’s decision-making process. The goal is to create a malware detection system that ensures both high accuracy and interpretability, enhancing its reliability and practicality in cybersecurity.},
        keywords = {},
        month = {February},
        }