基于认知诊断理论的网络安全自适应测试技术  

Adaptive Testing Technology Based on Cognitive Diagnostic in Cybersecurity

作　　者：齐斌 王宇 邹红霞 李冀兴 QI Bin;WANG Yu;ZOU Hong-xia;LI Ji-xing(Department of Information,Space Engineering University,Beijing 101416,China)

机构地区：[1]航天工程大学航天信息学院

出　　处：《计算机科学》2019年第7期102-107,共6页Computer Science

基　　金：国家863计划项目(2015AAxxx2078);省部级科技创新工程(ZYX14030011)资助

摘　　要：为进一步研究人员的网络安全素养,准确诊断人员网络安全知识和技能的水平,结合心理测量学和计算机测试技术,开发了基于认知诊断的多级属性评分的自适应测试技术。首先,为更好适应多元化复杂的网络安全知识结构且便于测试模型,在网络安全领域设计了复杂的层级网络安全知识库模型;然后,在多级评分认知诊断模型的基础上引入了属性层级的概念进行综合改进,并提出了准确、高效的参数估计方法和同模型相适应的选题策略。实验结果表明,多级属性评分的网络安全自适应测试技术较传统的多级评分模型提高了10.5%的效率,为计算机自适应测试领域的研究提供了参考。To further effectively study the cybersecurity literacy of personnel and accurately diagnose the specific level of personnel knowledge and skills,the paper developed adaptive cybersecurity testing technology based on multi-level attributes scoring of cognitive diagnosis by combining psychometrics and computer testing technology.Firstly,a hierarchical cybersecurity knowledge model is designed for better adapting to the complex knowledge structure and verifying the research.Then,the hierarchy of attribute is input based on polytomous scoring cognitive diagnosis model to implement comprehensive improvements.Accurate and efficient parameter estimation method and suitable selection strategy are proposed to improve performance.The experimental results show that the adaptive cybersecurity testing technology of multi-level attributes scoring improves the efficiency by 10.5%compared with the traditional multi-level scoring model,which provides a reference to the research of computerized adaptive testing.

关 键 词：自适应测试 认知诊断 网络安全 PH-DINA 素养测评 

分 类 号：TP309.2[自动化与计算机技术—计算机系统结构] TN915.08[自动化与计算机技术—计算机科学与技术]