基于N-Gram和TFIDF的SQL注入检测方法  

SQL Injection Detection Method Based on N-Gram and TFIDF

作　　者：苏林萍[1] 刘小倩 陈飞 李为 崔文超[1] SU Linping;LIU Xiaoqian;CHEN Fei;LI Wei;CUI Wenchao(School of Control and Computer Engineering,North China Electric Power University,Beijing 102206)

机构地区：[1]华北电力大学控制与计算机工程学院,北京102206

出　　处：《计算机与数字工程》2021年第6期1177-1181,共5页Computer & Digital Engineering

基　　金：国家自然科学基金项目“面向智能电网基础设施Cyber-Physical安全的自治愈基础理论研究”(编号:61300132)资助。

摘　　要：随着信息技术的不断发展,各种SQL注入攻击工具层出不穷,攻击类型多变万化,SQL注入问题一直是网络安全的主要问题。因此,针对SQL注入攻击提出一种基于N-Gram和TFIDF(term frequency inverse document frequency)的入侵检测方法。其核心思想是:首先在预处理阶段使用N-Gram技术选取特征词,再利用TFIDF技术进行SQL语句文本向量化处理,然后在此数据集基础上训练SVM分类器,最后通过与现有研究进行对比来检测分类效果。实验结果表明,与直接使用预先定义好的特征向量相比,此方法在保证召回率的基础上,准确率有所提高。With the continuous development of information technology,various SQL injection attack tools emerge one after an⁃other,and the types of attacks are varied.SQL injection has always been the main problem of network security.Therefore,this pa⁃per proposes an intrusion detection method based on N-Gram and tfidf(term frequency inverse document frequency).The core idea is using N-Gram to select feature words in the preprocessing stage and TFIDF to vectorize SQL sentences.Then on the basis of this data set the SVM classifier is trained.Finally,the classification effect is tested by comparing with existing research.Experimental re⁃sults show that,compared with using predefined feature vectors directly,this method can improve the accuracy on the basis of ensur⁃ing the recall rate.

关 键 词：网络安全 SQL注入 入侵检测 N-GRAM 文本向量化 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]