Research on Android Intent Security Detection Based on Machine Learning
Zhuo Lv, Zhimin Guo, Cen Chen · 2017
With the rapid development of mobile Internet, android system becomes the absolute overlord of the operating system, which has an unparalleled influence to the smart phone industry, but also closely related with people's lives. However, the feature of open source and lacking of regulatory of Android system led to a lot of security risks. Because of the widespread use of Android Intent Mechanism, the number of vulnerabilities of denial of service and authority to bypass due to the Intent mechanism is far ahead in recent years. In this paper, we focused on the detection of security vulnerabilities based on Intent mechanism and proposed a security detection model based on machine learning, which combines static detection and dynamic detection, and uses machine learning detectors to classify detection the Intent component. This model could be a better implementation of security vulnerability detection to help developers and Android project team to carry out security testing and maintenance better.