基于 Android 无障碍服务的行为监控

The abnormal behavior of users on mobile phones brings certain losses and risks to the country, society, enterprises and individuals. Such as, users record sensitive information of enterprises with the help of mobile phones, or use mobile phones to spread false statements on social networks. However, there is no technology to directly run on the termi⁃ nal to monitor the user's local application operation. Since most mobile phones are Android platforms, this paper takes An⁃ droid smart phones as the research object, and proposes a user behavior monitoring technology based on accessibility ser⁃ vice. When the phone's interface changes, there will be a large number of accessibility events written based on the view hi⁃ erarchy. Our method selects the key accessibility events, traverses them, obtains the information on interface component el⁃ ements, types of accessibility events, interface focus objects and so on, and then judges the user's behavior. Our method does not depend on a specific Android version; improves processing performance by filtering accessibility events; protects users' privacy by adjusting the application monitoring scope and monitoring granularity. In order to prove the feasibility of our method, we experiment on the devices in the physical world and correctly monitor the behavior of users in four different applications. Performance testing shows that our method has low CPU consumption and low average memory occupancy.