Explainable Attention-Guided Stacked Graph Neural Networks for Malware Detection
Researchers have developed a novel ensemble framework using stacked graph neural networks (GNNs) for improved malware detection. This method dynamically extracts control flow graphs from executable files and uses multiple GNN base learners to capture diverse behavioral features. An attention-based meta-learner aggregates predictions and provides explanations by quantifying the contribution of each base model, enhancing interpretability and robustness. AI
IMPACT Enhances the interpretability and accuracy of AI-driven malware detection systems.