网络教学课程信息窃取风险实时监测方法研究  

Research on Real-time Monitoring Method of Information Stealing Risk in Network Teaching Course

作　　者：安心 王涛[2] AN Xin;WANG Tao(Xi’an Aeronautical Polytechnic Institute,Xi’an 710089,China;Xi’an Aeronautical University,Xi’an 710077,China)

机构地区：[1]西安航空职业技术学院,西安710089 [2]西安航空学院,西安710077

出　　处：《自动化与仪器仪表》2023年第1期20-25,共6页Automation & Instrumentation

基　　金：2021年度陕西高等职业教育教学改革研究项目重点攻关课题《课程思政背景下高职院校民航服务类专业信息化教学改革研究与实践》(21ZG001)。

摘　　要：针对传统网络教学课程信息软件漏洞检测准确率低,导致网络教学课程信息的窃取风险增大的问题。构建一个基于时间卷积网络和自注意力机制的漏洞检测系统TCNSADetector。首先,采用时间卷积网络TCN的TCNDetector系统进行漏洞特征自动提取;然后通过自注意力机制的漏洞检测系统VulDeePecker+进行深层特征提取和分类;最后将时间卷积网络和自注意力机制相结合,得到TCNSADetector漏洞检测系统。实验结果表明,相较于其他漏洞检测系统,提出的TCNSADetector系统的F1值提升了4.97%,误报率和漏报率分别下降了5.42%和3.68%,漏洞检测时间均低于其他检测系统。而加入注意力机制后的TCNSADetector漏洞检测系统准确率、精确率和F1值均保持在96%以上,比改进前的漏洞检测系统更高。综合分析可知,本系统可提升网络教学课程信息软件的漏洞检测精度,具备实时性和有效性。The low detection accuracy of vulnerability of traditional network teaching course information software leads to the increased risk of network teaching course information theft.TCNSADetector,a vulnerability detection system based on temporal convolutional network and self-attention mechanism.First,the TCNDetector system of time convolution network TCN is used to automatically extract vulnerability features;then the deep feature extraction and classification is performed through VulDeePecker+,a vulnerability detection system of self-attention mechanism;finally,the time convolutional network and self-attention mechanism are combined to obtain the TCNSADetector vulnerability detection system.The experimental results show that compared with other vulnerability detection systems,the F1 value of the proposed TCNSADetector system increased by 4.97%,the false alarm rate and false report rate decreased by 5.42%and 3.68%,respectively,and the vulnerability detection time was lower than that of other detection systems.However,the accuracy,accuracy rate and F1 value of the TCNSADetector vulnerability detection system after adding the attention mechanism all remain above 96%,which is higher than the vulnerability detection system before the improvement.Comprehensive analysis shows that the system can improve the vulnerability detection accuracy of the network teaching course information software,with real-time and effectiveness.

关 键 词：网络教学 课程信息窃取 漏洞检测 时间卷积网络 自注意力机制 

分 类 号：TP392[自动化与计算机技术—计算机应用技术]