Android application behavior representation construction method based on execution track information

Abstract

The invention discloses an Android application behavior representation construction method based on execution track information, and the method comprises the steps: collecting the execution track information of a target Android application, and constructing a data model based on the execution track information, wherein the execution track information comprises a plurality of execution tracks, and the data model is a function call tree (FCT); determining a preferred keyword list corresponding to the execution track according to a function call tree (FCT), and determining a vocabulary corresponding to the execution track information according to the preferred keyword list; and according to the vocabulary and the preferable keyword list, constructing behavior representation corresponding to the execution track information. According to the method, modeling is carried out according to the execution track information of the target Android application, the keywords are extracted according to the modeled data model, the semantic consistency Android application behavior representation is constructed according to the keywords, and when the Android application behavior representation is applied to Android application function recognition, the function identification accuracy of the Android application can be obviously improved. 本发明公开了基于执行轨迹信息的安卓应用行为表征构造方法，方法包括：采集目标安卓应用的执行轨迹信息，并基于执行轨迹信息构建数据模型；其中，执行轨迹信息包括若干执行轨迹；数据模型为函数调用树FCT；根据函数调用树FCT，确定与执行轨迹对应的优选关键词列表，并根据优选关键词列表，确定与执行轨迹信息对应的词汇表；根据词汇表和优选关键词列表，构造与执行轨迹信息对应的行为表征。本发明申请根据目标安卓应用的执行轨迹信息进行建模，根据建模后的数据模型来提取关键词，根据关键词来构造语义一致性的安卓应用行为表征，当将安卓应用行为表征应用于安卓应用功能识别时，可以显著提高安卓应用功能识别准确率。