Rogue Android application program detecting method based on deep learning
An Android application and application technology, applied in neural learning methods, computer security devices, biological neural network models, etc., can solve problems such as single feature detection, inability to comprehensively analyze applications, and difficulty in detecting malicious applications. Detect the effect of accurate and accurate identification
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0031] The process of DeepDroid algorithm security detection for Android applications is divided into three steps: first, obtain application feature vectors, perform static analysis and dynamic analysis on applications in training set and test set respectively, extract static features and dynamic features and integrate them into The feature vector of the application program; then use the extracted feature vector of the training set application program to train the DBN network; finally, input the feature vector of the test set application program into the trained DBN network for security detection. The structure diagram of the DeepDroid algorithm is as follows figure 1 shown.
[0032] The feature vector is composed of 126 static features and dynamic features. The first 41 features are static features. The static features include 8 third-party unavailable permissions and 33 typical application common permissions. The last 85 features are dynamic features. Dynamic features inclu...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 
PatSnap Eureka turns technology decisions into work you can execute. Powered by our Innovation Knowledge Graph, it runs expert workflows across engineering, life sciences, materials and intellectual property. Get your review-ready output in minutes.
