DeepAutoD: Research on Distributed Machine Learning Oriented Scalable Mobile Communication Security Unpacking System

Abstract

The rapid growth of Android smart phones and abundant applications (Apps), a new security solution for distributed computing and mobile communications, has prompted many enhanced vendors to use different methods to effectively protect important Android files on distributed systems / servers. However, it also brings some serious distributed security problems: for example, malicious applications use reinforcement methods to hide their high-risk code, and even hide in normal applications to avoid being detected by anti-virus engines. This makes it more difficult to filter or detect malware applications. In serious cases, it will greatly affect the efficiency of mobile communication and threaten the security of distributed computers. In this paper, we propose a generic and easy to deploy and extend unpacking framework called DeepAutoD (hereinafter referred to as d-ad). By eliminating the influence of reinforcement, the framework outputs the original DEX files containing malicious features, which can provide complete feature information input for distributed machine learning based on malicious code detection. The unpacking technology solution we use integrates the deep deception call chain, which can detect the mainstream applications in the application market in a short time (a large number of malicious code will be hidden in the conventional applications), and the algorithm can adapt to any high version of Android system. Data analysis and experimental results show that the program is superior to the existing main programs in terms of safety and effectiveness.