Intelligent Pattern Recognition Using Equilibrium Optimizer With Deep Learning Model for Android Malware Detection

Abstract

Android malware recognition is the procedure of mitigating and identifying malicious software (malware) planned to target Android operating systems (OS) that are extremely utilized in smartphones and tablets. As the Android ecosystem endures to produce, therefore is the risk of malware attacks on these devices. Identifying Android malware is vital for keeping user data, privacy, and device integrity. Android malware detection utilizing deep learning (DL) signifies a cutting-edge system for the maintenance of mobile devices. DL approaches namely recurrent neural network (RNN) and convolutional neural network (CNN) are best in automatically removing intricate designs and behaviors in Android app data. By leveraging features such as application programming interface (API) call sequences, code patterns, and permissions, these approaches are efficiently differentiated between benign and malicious apps, even in the face of previous unseen attacks. This study presents an Intelligent Pattern Recognition using an Equilibrium Optimizer with Deep Learning (IPR-EODL) Approach for Android Malware Recognition. The purpose of the IPR-EODL approach is to properly identify and categorize the Android malware in such a way that security can be achieved. In the IPR-EODL technique, the data pre-processing step was applied to convert input data into a compatible setup. In addition, the IPR-EODL technique applies channel attention long shortterm memory (CA-LSTM) methodology for the recognition of Android malware. To enhance the solution of the CA-LSTM algorithm, the IPR-EODL system employs the Equilibrium optimization (EO) algorithm for the hyperparameter tuning method. The experimentation evaluation of the IPR-EODL model can be verified on a benchmark Android malware database. The extensive results highlight the significant result of the IPR-EODL approach to the Android malware detection process.