Explainable AI for Mobile Security: A Hybrid Approach to Android Malware Detection

Abstract The rise in Android malware shows that mobile security needs better ways to find and understand threats. The goal of this study is to create a strong, clear framework for finding Android malware. We present a hybrid feature fusion methodology that integrates static metadata (permissions, intents), dynamic API requests (exceeding 23,000 behavioral indicators), and DEX image-based features derived from a convolutional neural network. The approach uses a dataset of 74,268 APK samples from a public repository. Of these, 18,440 are benign and 55,828 are malicious. The dataset is split into 70\% for training, 10\% for validation, and 20\% for testing. Our results show that we got a perfect 100\% accuracy on the test set, which is better than other methods. Explainable AI approaches find the most important factors that affect classification, like questionable permissions and API requests related to the network. These techniques make it easier for non-technical users to understand. This work is new because it combines multi-modal characteristics with interpretable AI to create a scalable, clear solution for finding Android malware in the real world.