The tremendous development of smartphones has led to a significant increase in free Android-based apps. This leads to numerous malicious activities that violate security norms and user privacy. Malware detection on Android-based devices is one of the growing issues due to the undesirable similarity between malicious features and natural elements. This can lead to slow detection and long-term storage on affected devices. The popularity of the platform and its public features make Android devices a prime target for attackers. As the Android market continues to evolve, it is crucial to develop specialized tools to detect attacks against Android-based platforms. Hence, this research work discloses a novel framework for identifying malware in the Android implemented applications with the help of DL (Deep Learning) methodologies such as enhanced CNN based DenseNET 169 and 201. The proposed approach was tested and trained using Malevis and Malimg Dataset. The results obtained from the experimental procedures demonstrate that the proposed deep learning framework outperforms the various traditional methods with an accuracy of 96.09–98.40%.