摘要
Android恶意软件检测数据集中存在大量不相关和冗余的特征,单一的特征选择方法并不能有效去除不相关或冗余特征.如果移除信息量较大的特征则容易引发模型崩塌的问题.针对以上问题,提出一种基于三支决策特征选择(three-way decision feature selection,3WDFS)的安卓恶意软件检测方法.该方法结合三支决策的思想,并行使用多种特征选择方法评估数据集的特征,将特征分为不相交的正域、负域和边界域;然后,分别利用近似马尔可夫毯和信息量差异删除边界域中的类间冗余特征和类内冗余特征,形成低冗余的边界域;最后,通过可学习权重参数级联拼接正域和低冗余边界域,输入分类模型训练学习.在公开数据集上的实验结果表明,3WDFS能够有效删除Android恶意软件检测中不相关和冗余的特征,提高检测恶意软件的检测效率和准确率.
There are a large number of irrelevant and redundant features in the Android malware detection dataset.A single feature selection method cannot effectively remove irrelevant or redundant features.If the features with large amount of information are removed,it is easy to cause the problem of model collapse.To address these issues,this paper proposed an Android malware detection method based on Three-Way Decision Feature Selection(3WDFS).The algorithm combines the idea of three-way decision,and uses a variety of feature selection methods to evaluate the features of the dataset in parallel.The features are divided into disjoint positive region,negative region and boundary region.Then,the inter-class redundancy feature and the intra-class redundancy feature in the boundary region are deleted by using the approximate Markov blanket and the information difference respectively to form a low-redundancy boundary region.Finally,the positive region and the low redundancy boundary region are concatenated by the learnable weight parameter,and the classification model is input for training and learning.Experimental results on public datasets show that 3WDFS can effectively remove irrelevant and redundant features in Android malware detection and improve the detection efficiency and accuracy of malware detection.
作者
陈丽芳
王嘉优
施永辉
韩阳
代琪
Chen Lifang;Wang Jiayou;Shi Yonghui;Han Yang;Dai Qi(College of Science,North China University of Science and Technology,Tangshan,Hebei 063210;Hebei Key Laboratory of Data Science and Application(North China University of Science and Technology),Tangshan,Hebei 063210)
出处
《信息安全研究》
北大核心
2025年第6期561-568,共8页
Journal of Information Security Research
基金
国家自然科学基金面上项目(52074126)。
