Android malicious application detection method and system based on parallel ensemble learning

Abstract

The invention discloses an Android malicious application detection method and system based on parallel ensemble learning, and the method comprises the steps: carrying out the reverse engineering of a to-be-detected Android application, obtaining a source code file and a configuration file of the to-be-detected Android application, and extracting static behavior characteristics from the source code file and the configuration file; screening the static behavior characteristics; constructing behavior feature vectors according to the screened static behavior features; and constructing a parallel integrated learning model according to the behavior feature vector and a machine learning algorithm, and detecting the Android malicious application according to the parallel integrated learning model. The system provided by the invention comprises an extraction module, a filtering module, a first processing module, a second processing module and a detection module. According to the method and the system provided by the invention, the Android malicious application can be comprehensively, efficiently and accurately detected by comprehensively extracting the static behavior characteristics, screening the static behavior characteristics and constructing the parallel integrated learning model.

Description

technical field [0001] The invention relates to the technical field of network security, in particular to a method and system for detecting Android malicious applications based on parallel integrated learning. Background technique [0002] The Android platform and its applications have gradually replaced PCs and become the preferred electronic devices for people's daily work, life and entertainment due to their diverse functions and flexible use. However, due to the large amount of user privacy data stored on Android smartphones, such as confidential documents, contact information, bank card accounts, etc., and the open source nature of the Android platform, the technical threshold for creating malicious applications is lowered, and the number of Android malicious applications has increased sharply. growth and diversification. The "McAfee Labs Threat Report" released by McAfee, the world's leading network security company, in November 2017 showed that more than 12 million A...

AI Technical Summary

Problems solved by technology

Malicious Android applications bring harm to governments, enterprises, and individual users through some malicious behaviors, such as stealing private information, malicious deduction, rogue behavior, etc., and even cause huge economic losses

Existing research work has laid a solid foundation for Android malicious application detection. However, in specific model applications, most research tends to focus on the analysis and detection of Android malicious applications usin

Images