DynaShield:Android Malware Detection Using Dynamic Analysis of Network Traffic

In an era where mobile applications are integral to daily life, safeguarding Android devices from malicious threats has become a paramount concern. This project addresses the pressing issue of Android malware detection by developing a robust detection system that leverages diverse datasets and advanced machine learning techniques. By incorporating permission-based, network traffic-based, API call-based, opcode-based, system call-based, binary-based, and behavior-based datasets, our approach aims to provide a comprehensive and accurate detection mechanism. Through rigorous evaluation using metrics such as accuracy, precision, recall, and F1-score, we aim to achieve a system that not only identifies known malware but also uncovers previously unseen threats. This paper presents the methodology, implementation, and performance analysis of the proposed system, offering valuable insights into the future of mobile security.