Android malicious application detection method based on dual-channelconvolutional neural network

A malicious application, convolutional neural network technology, applied in the field of Android malicious application detection based on dual-channel convolutional neural network, can solve problems such as threats to user market security, and achieve reduced attack probability, high classification accuracy and high accuracy. The effect of recall

Active Publication Date: 2019-01-08
CIVIL AVIATION UNIV OF CHINA
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The dominant market share of the Android system and its openness provide a good environment for the spread of malicious applications, resulting in a large number of malicious applications being downloaded and used, which seriously threatens the security of users and the market.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Android malicious application detection method based on dual-channelconvolutional neural network
  • Android malicious application detection method based on dual-channelconvolutional neural network
  • Android malicious application detection method based on dual-channelconvolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, but the following embodiments in no way limit the present invention.

[0024] Such as figure 1 As shown, the Android malicious application detection method based on dual-channel convolutional neural network provided by the present invention includes the following steps carried out in order:

[0025] 1) Obtaining installation package files of benign applications and malicious applications;

[0026] Obtain installation package files of benign and malicious applications from app stores, web forums or research institutions;

[0027] 2) Decompile each installation package file obtained in step 1) to obtain the decompiled folder of the application, and then extract the file with the suffix .smali under the smali folder in the decompiled folder, and traverse and read the above All files with the suffix .smali;

[0028] 3) Write a Python script, extra...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

An Android malicious application detection method based on a dual-channel convolutional neural network is provided. The method includes obtaining an installation package file; decompiling the installation package files; constructing an opcode sequence; construct an instruction function sequence; carrying out vectorization processing on the features of the operation code sequence and the instruction function sequence; training a convolutional neural network; testing the convolutional neural network; evaluating the malicious application detection model; detecting an application to be detected, etc. Compared with the traditional detection model, the malicious application detection model generated by the method provided by the invention has higher classification accuracy and recall rate, and reduces the probability of the Android system being attacked due to missing detection.

Description

technical field [0001] The invention belongs to the technical field of software security, in particular to a method for detecting malicious Android applications based on a dual-channel convolutional neural network. Background technique [0002] The dominant market share of the Android system and its openness provide a good environment for the spread of malicious applications, resulting in a large number of malicious applications being downloaded and used, which seriously threatens the security of users and the market. Due to the security problems caused by the prevalence of Android malicious applications, the detection of Android malicious applications has become a current research hotspot. [0003] Feizollah A et al. evaluated the effectiveness of Android Intents as a feature to identify malicious applications, found that Intents is a feature that can describe applications, and believed that this feature should be used in combination with other features. Zhang Rui and Yang...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F21/56
CPCG06F21/562G06F21/563G06F2221/033
Inventor 杨宏宇那玉琢谢丽霞
Owner CIVIL AVIATION UNIV OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap