This research presents the AMDDLmodel, a deep learning approach for Android malware detection. The model employs a Convolutional Neural Network (CNN) to detect and classify Android malware based on various parameters such as filter sizes, number of epochs, learning rates, and layers. The model was evaluated using the Drebin dataset, which contains 215 features extracted from 15,036 Android applications, including 5,560 malware and 9,476 benign applications. The model achieved an accuracy of 99.92%, with precision of 98.61%, recall of 99.16%, and an F1-score of 98.88%. These results indicate that the AMDDLmodel outperforms existing techniques in Android malware detection. The model's performance was further validated through a confusion matrix, training and validation accuracy, and loss graphs. The results show that the model has high accuracy and low loss, making it an effective tool for Android malware detection. The study also discusses the limitations of the model and suggests future research directions, including the use of broader datasets, enhancing model interpretability, and addressing scalability issues. The AMDDLmodel demonstrates superior performance in detecting Android malware, providing a practical solution for improving device security.This research presents the AMDDLmodel, a deep learning approach for Android malware detection. The model employs a Convolutional Neural Network (CNN) to detect and classify Android malware based on various parameters such as filter sizes, number of epochs, learning rates, and layers. The model was evaluated using the Drebin dataset, which contains 215 features extracted from 15,036 Android applications, including 5,560 malware and 9,476 benign applications. The model achieved an accuracy of 99.92%, with precision of 98.61%, recall of 99.16%, and an F1-score of 98.88%. These results indicate that the AMDDLmodel outperforms existing techniques in Android malware detection. The model's performance was further validated through a confusion matrix, training and validation accuracy, and loss graphs. The results show that the model has high accuracy and low loss, making it an effective tool for Android malware detection. The study also discusses the limitations of the model and suggests future research directions, including the use of broader datasets, enhancing model interpretability, and addressing scalability issues. The AMDDLmodel demonstrates superior performance in detecting Android malware, providing a practical solution for improving device security.