Dynamic detection method for android malicious software based on mimicry of enhanced deep learning

Abstract

The invention discloses a dynamic detection method for android malicious software based on an enhanced deep learning mimicry. In the method, an android malicious software dynamic detection model based on the enhanced deep learning mimicry is constructed; and based on the model, the method comprises the following steps: carrying out data preprocessing on input data, and then inputting the preprocessed data into a heterogeneous redundant model structure, wherein the heterogeneous redundant model structure comprises three heterogeneous redundant bodies with equivalent functions, and the three heterogeneous redundant bodies are respectively an enhanced Long Short Term Memory Network (LSTM) model, an enhanced Gated Recurrent Unit (GRU) model and an enhanced capsule network model. According to the method provided by the invention, in the android malicious software dynamic detection model based on the mimicry architecture, the mimicry architecture and the mimicry defense principle are utilized, so that the model can autonomously defend the attack of the network, and the defensive performance of the model is enhanced.

Description

technical field [0001] The disclosure of the present invention relates to the technical field of mobile Internet security, in particular to a dynamic detection method for Android malware based on enhanced deep learning mimicry. Background technique [0002] In recent years, the Android operating system has gained popularity due to the open nature of the Android framework. With the widespread use of the Android operating system, the number of Android software has also increased significantly. The rapid development of Android software has made lawbreakers turn their attention to the Android software development market, using Android malicious software to steal the privacy of Android users and seek illegal benefits. While the number of Android software is increasing, the amount of Android malware is also increasing year by year. [0003] While the number of Android malware has grown rapidly, its evasion techniques have also developed rapidly in recent years. In 2020, Google ...

AI Technical Summary

Problems solved by technology

[0004] In response to the above situation, although a variety of Android malware detection methods have been proposed in recent years, with the continuous increase in the number of Android malware and the continuous upgrading of attack methods, the current situation of mobile network security is still very severe.

Images