Published Paper Details:

The latest smartphone stages built on new operating systems, such as iOS, Android, or Windows Phone, have been a vast achievement in recent years and built up various new opportunities. Unfortunately, 2011 also indicated to us that the new machinery and the privacy-related documents on smartphones are also gradually fascinating for attackers. In this project, mobile app malware detection, which contains a Recurrent Neural Network (RNN) classification algorithm is implemented. The malware detection data set is analyzed that contains 35 features to study the viability of classification algorithm and malware detection is made by using the LSTM method to achieve more accuracy. The unique malware dataset patterns obtained by this method is converted to their binary form and it is applied to the deep learning algorithm to classify the malware and benign files. In this method, the malware can be predicted with 98.89% accuracy using Long Short-Term Memory (LSTM) which outperforms Malware detection-based methods.