基于机器学习的SQL攻击检测技术研究  

Research on SQL attack detection technology based on machine learning

作　　者：张泽亚 翟健宏[1] ZHANG Zeya;ZHAI Jianhong(School of Computer Science and Technology,Harbin Institute of Technology,Harbin 150001,China)

机构地区：[1]哈尔滨工业大学计算机科学与技术学院,哈尔滨150001

出　　处：《智能计算机与应用》2020年第3期356-361,共6页Intelligent Computer and Applications

摘　　要：SQL注入是网络上使用非常广泛的攻击手段,也是防御难度极大的网络攻击方式。在信息安全领域中,SQL注入因其适用范围广,操作门槛低,可造成的损失大而被视为对网络安全威胁极大的一类攻击方式。本论文的目的在于测试不同的机器学习算法对于SQL注入攻击的区分能力。研究搜集了大量的SQL注入攻击语句,选择4种不同的机器学习模型建立了分类器,并使用上面收集的数据对其进行了训练。最后,对4种算法所建立的分类器进行了测试,得出了最适合检测SQLM AP的机器学习算法是卷积神经网络(CNN)算法。In the field of information security,SQL injection is regarded as a kind of attack mode which threatens the network security greatly because of its wide application range,low operation threshold and great loss.The purpose of this paper is to test different machine learning algorithms for distinguishing SQL injection attacks.The paper collects a large number of SQL injection attack statements,selects four different machine learning models to build classifiers,and uses the data collected above to train them.Finally,the paper tests the classifiers built by the four algorithms and concludes that the most suitable machine learning algorithm for detecting SQLMAP is convolutional neural network(CNN)algorithm.

关 键 词：SQL注入攻击 决策树 机器学习 分类器算法 SQLMAP 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]