Explainable Attention-Guided Stacked Graph Neural Networks for Malware Detection

ArXi:2508.09801v3 Announce Type: replace-cross Malware detection in modern computing environments demands models that are not only accurate but also interpretable and robust to evasive techniques. Graph neural networks (GNNs) have shown promise in this domain by modeling rich structural dependencies in graph-based program representations such as control flow graphs (CFGs). However, single-model approaches may suffer from limited generalization and lack interpretability, especially in high-stakes security applications.