Application identification methods, application identification system and related equipment

Abstract

The embodiment of the invention discloses application identification methods, an application identification system and related equipment. The method includes: obtaining a target log data set of a target application; generating a target time behavior vector, which corresponds to the target log data set, according to a service behavior type corresponding to each piece of log data in the target log data set; generating a target probability behavior vector, which corresponds to the target log data set, according to the service behavior type corresponding to each log data in the target log data set; extracting target time-sequence feature information of the target time behavior vector; extracting target space feature information of the target probability behavior vector; carrying out feature fusion on the target space feature information and the target time-sequence feature information to obtain target fusion feature information; and identifying the application security type of the target application according to the target fusion feature information. By using the method, accuracy of application identification can be improved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to an application identification method, system and related equipment. Background technique [0002] In recent years, the Android (Android) platform has become a very popular mobile phone operating system platform, and has occupied more than half of the mobile phone operating system market share in the world. With the popularization of Android smartphones and Android tablets, malicious applications based on Android are also developing rapidly. Malicious applications are aimed at destroying the system, stealing privacy, maliciously deducting fees, and consuming traffic. They are mainly divided into Trojan horses, backdoors, worms, botnets, offensive advertisements, spyware, etc. Malicious applications carry offensive operation instructions and cause huge damage to users. economic loss. [0003] The existing application identification method is mainly that the terminal dev...

AI Technical Summary

Problems solved by technology

However, viruses in malicious applications mutate quickly and grow in large numbers. If the identification of malicious applications only depends on the number of blacklists in the cloud server, there is a lag in identifying malicious applications and it is difficult to effectively and continuously detect malicious applications.

[0004] It can be seen from the above that the identification accuracy rate of the application identification method based on the blacklist in the cloud server is low, and it is difficult to accurately and continuously identify the security of the application in the terminal device.

Images