混合特征的涉诈类APP分析模型的构建与研究
Research on analysis model of fraud-related APP based on mixed features
夏艺丹 1李乔宇 1施俊帆1
作者信息
- 1. 浙江警察学院,浙江 杭州 310000
- 折叠
摘要
针对涉诈类APP分类难的问题,通过N-gram、主成分分析法等方法对Dalvik字节码与权限特征形成的特征码进行降维,利用K-Means++聚类算法构建APK涉诈家族分析模型,实现对涉诈类APP进行分类的目的.
Abstract
Aiming at the problem of difficult classification of fraud-related APPs,N-gram,principal component analysis and other methods are used to reduce the dimension of the feature codes formed by Dalvik bytecode and permission features,and K-Means++ clustering algorithm is used to construct the analysis model of APK fraud-related family,so as to achieve the purpose of classifying fraud-related APPs.
关键词
涉诈类APP/Dalvik字节码/权限/K-Means++Key words
fraud-related APP/Dalvik bytecode/permission/K-Means++引用本文复制引用
出版年
2023
NETL
NSTL
维普
万方数据