Intelligent Mobile Malware Detection

This book provides essential strategies for developing intelligent detection mechanisms against Android malware, crucial for researchers and cybersecurity professionals.

The rise in popularity of Android mobile phones has unfortunately attracted cybercriminals, leading to the creation of malware applications that engage in a variety of malicious activities. This book serves as a vital resource for Android malware researchers, developers, students, and cybersecurity professionals, aiming to explore and establish defense mechanisms against these threats. The urgency of addressing Android malware has become increasingly apparent, especially following the surge in attacks during the COVID-19 pandemic, underscoring the need for robust protection strategies.

In this comprehensive guide, readers will learn how to develop intelligent detection mechanisms for Android malware by employing various graph and stochastic models. The book opens with an introduction to the Android operating system, highlighting the limitations of current static malware detection methods. It then delves into a hybrid detection mechanism that combines multiple approaches for improved efficacy. Furthermore, the text explores four distinct system call-based dynamic detection mechanisms, utilizing advanced techniques such as graph centrality measures, graph signal processing, and graph convolutional networks.

The authors share their recent research findings, demonstrating how the detection of Android malware can often hinge on identifying unique subsequences within system call sequences. The experiments detailed in the book utilize the latest malware samples sourced from public repositories, and the inclusion of source codes facilitates easy implementation of the proposed detection mechanisms. Overall, this work is an essential tool for anyone involved in the fight against evolving Android malware.