Android Malware Detection System: a Review and Research Directions
Oforjetu Chukwudi Peter, Moshood Abiola Hambali, Salau-Ibrahim Taofeekat Tosin, Andrew Ishaku Wreford, Chukwudi Jennifer Ifeoma · International Review on Computers and Software (IRECOS) · 2024
The prevalence of malware in the cloud ecosystem has become a global epidemic, with a wide variety of malware programs emerging over the years, specifically targeting computer systems. These malware programs aim to either steal confidential information or demonstrate the capabilities and skills of the attackers. In order to combat these malicious codes, traditional approaches have relied on static signature-based techniques, commonly employed by anti-malware programs. While this approach effectively detects and blocks known malware, it falls short in identifying new variations of malware. Therefore, this paper presents a survey that explores dynamic techniques for malware detection, specifically focusing on machine learning and deep learning approaches. The study encompasses various approaches to detecting malware in the Android ecosystem.