基于云计算和深度学习的协议监测系统设计  

Design of Protocol Monitoring System Based on Cloud Computing and Deep Learning

作　　者：雷惊鹏[1] Lei Jingpeng(School of Information Technology,Anhui Vocational College of Defense Technology,Lu an,Anhui 237011)

机构地区：[1]安徽国防科技职业学院信息技术学院,安徽六安237011

出　　处：《信息安全研究》2020年第12期1127-1132,共6页Journal of Information Security Research

基　　金：安徽省2018年度高校自然科学研究重大项目(KJ2018ZD066);安徽省2017年度高校优秀拔尖人才培育资助项目(gxyq2017182)。

摘　　要：各类Web应用的发展,使得HTTP协议应用范围不断扩大.由于Web技术的灵活性、多样性特征,针对Web应用新的攻击方法也在不断产生和演变.类似XSS跨站脚本攻击、数据库注入攻击等恶意行为越来越多地体现在HTTP请求中.传统安全防御体系无时无刻不在应对新的挑战.为了应对Web安全新变化,提出建立HTTP协议安全监测模型,针对模型进行分类算法训练,检测HTTP访问数据类别的方法.结合恶意行为在HTTP请求中形式多变、恶意特征路径多变、监测存在难度的特点,探索利用云计算机技术分析HTTP请求格式和恶意特征,自动生成敏感词数据库,通过基于信息熵的特征选择算法,结合深度学习技术设计分类算法训练安全检测模型,进而提出改进HTTP协议安全的监测系统.The development of various types of Web applications has enabled the application range of the HTTP protocol to continue to expand.Due to the flexibility and diversity of Web technologies,new attack methods for Web applications are constantly generating and evolving.Malicious behaviors such as XSS cross-site scripting attacks and database injection attacks are increasingly reflected in HTTP requests.The traditional security defense system responds to new challenges all the time.In order to cope with the new changes of Web security,this paper proposes a method to establish the HTTP protocol security monitoring model,the classification algorithm training for the model,and the detection of HTTP access data categories.Combining the characteristics of the change of in HTTP request form the change of malicious feature path,and the difficulty of monitoring,explore the use of cloud computer technology to analyze HTTP request format and malicious features,automatically generate sensitive word database,and adopt feature selection algorithm which is based on entropy.In combination with deep learning technology,the classification algorithm is used to train the security detection model,and then a monitoring system for improving the security of the HTTP protocol is proposed.

关 键 词：云计算 深度学习 协议 监测系统 恶意代码 

分 类 号：TP393.0[自动化与计算机技术—计算机应用技术]