A Multifaceted Deep Generative Adversarial Networks Model for Mobile Malware Detection

Malware’s structural transformation to withstand the detection frameworks encourages hackers steal public’s confidential content. Researchers are developing a protective shield against intrusion of malicious malware in mobile devices. The deep learning-based android have ensured public safety; however, their dependency on diverse training samples has constrained utilization. handcrafted mechanisms achieved remarkable performance, but computational overheads major hurdle In this work, Multifaceted Deep Generative Adversarial Networks Model (MDGAN) been developed detect hybrid GoogleNet and LSTM features grayscale API sequence processed pixel-by-pixel pattern through conditional GAN for robust representation APK files. generator produces syntactic differentiation discriminator network. Experimental validation combined AndroZoo Drebin database shown 96.2% classification accuracy 94.7% F-score, which remain superior recently reported frameworks.