A Hybrid Deep Learning Approach for Android Malware Detection

The task of detecting malware on Android devices has become increasingly critical in the light of the widespread use of mobile devices and the escalating menace posed by malicious software. In the present scholarly publication, we put forth an innovative methodology for identifying malicious software within Android applications. Our proposed technique involves the utilisation of a hybrid recurrent neural network-convolutional neural network (RNN-CNN) architecture. The hybrid model effectively utilises the inherent advantages of both recurrent neural networks (RNNs) and convolutional neural networks (CNNs) in order to enhance the precision and efficacy of malware detection. We present a comprehensive methodology, including the architecture of the hybrid model and the CNN and RNN component parameters. The experimental findings serve to substantiate the efficacy of the proposed methodology in accurately discerning instances of Android malware.