Android Malware Detection Using Convolutional Neural Networks and Light Gradient Boosting Machine: A Hybrid Method

In the evolving landscape of Android malware detection, where threats are becoming increasingly sophisticated, our study introduces an advanced detection model that employs Convolutional Neural Networks (CNN) for feature extraction, followed by prediction using Light Gradient Boosting Machine (LGBM). This approach harnesses the power of deep learning to enhance feature identification and leverages LGBM's efficient predictive accuracy. Experimental validation of our model yielded remarkable results, with both accuracy and F1 score reaching 96.73%, showcasing the potential of integrating CNN and LGBM in combating malware challenges.