Malware Detection A Framework for Reverse Engineered Android Application through Machine Learning Algorithms

Abstract

This smartphone operating system is rapidly gaining popularity. Consequently, Android has emerged as an attractive focus for malicious attackers. They are concealing harmful algorithms in complex ways within Android apps, making it challenging for security firms for the purpose of recognizing and categorizing these apps as malware. The evolution pertaining to Android malicious software has reached a point where it can avoid typical detection methods due to its uniqueness. Machine learning-based approaches have surfaced as a more effective solution to address the issue complexity of emerging Android threats. These approaches the actions exhibited by existing malware patterns and use this data for the purpose of differentiation between known dangers and new risks. This study focuses on identifying vulnerabilities in mobile apps by utilizing Backward Designed Android. Key Words: SVM, AdaBoost, Ransomware, Android, Machine Learning