Efficient Android malware detection model DroidDet based on rotating forest
A malware and detection model technology, applied in the field of information security, can solve the problems of complexity, low accuracy, and high cost of human intervention in environment construction, achieving high efficiency and overcoming low accuracy.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Benefits of technology
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0036] The present invention will be further described below in conjunction with the accompanying drawings.
[0037] from figure 1 The overall framework of the present invention shows that the present invention mainly consists of two parts of work, one part is feature extraction and the other part is classifier. In the feature extraction part, use the apktool.jar decompilation tool to decompile the APK files of all Apps in the training set, then analyze and extract features such as permissions, system monitoring events, sensitive APIs, and permission rates, and perform PCA on these extracted features Processing to achieve normalization of features and retain the strongest principal components in the features to avoid noise interference in the extracted features. In addition, the Bootstrap self-service sampling method is used for sample interference to achieve the maximum diversity of the base learner. In the classifier part, an Android malware prediction model is constructed ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com