基于软件行为的可信评价研究  

Research of Trustworthiness Evaluation Model Based on Software Behavior

作　　者：丁卫涛[1] 徐开勇[1] 

机构地区：[1]解放军信息工程大学密码工程学院,郑州450001

出　　处：《计算机科学》2016年第1期202-206,225,共6页Computer Science

基　　金：国家自然科学基金项目:密码片上系统安全模型结构与验证方法研究(61072047)资助

摘　　要：为了准确合理地评价软件可信性,提出了基于软件行为的可信评价模型。首先,在软件行为迹中设置监控点,根据监控点各属性的性质及其在可信评价系统中的作用,将监控点的属性分为控制流和数据流两级。其次,针对控制流级属性,提出基于支持向量机(Support Vector Machine,SVM)的软件行为迹的评价方法;针对数据流级属性,提出基于模糊层次分析法的场景属性评价方法。最后,实验分析表明,基于软件行为的可信评价模型能够准确地评价软件可信性,并且具有较高的效率。In order to evaluate the trustworthiness of the software accurately and reasonably,a trustworthiness evaluation model based on software behavior was proposed.Firstly,the monitoring points are set up in the software behavior trace.According to the attribute of the monitoring points and the function in the trusted evaluation system,the monitoring points are divided into control flow and data stream.Secondly,for the attribute of control flow,the evaluation method of the software behavior trace based on support vector machine（SVM）is proposed.And for the attribute of data stream,the evaluation method of scene property based on fuzzy AHP is proposed.Finally,the experimental analysis shows that the trustworthiness evaluation model based on software behavior can evaluate the trustworthiness of software accurately and the efficiency.

关 键 词：软件行为 支持向量机 模糊层次分析法 监控点 软件可信 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]