基于机器学习的Java代码注入攻击漏洞识别  

Machine Learning-based Java Code Injection Attack Vulnerability Identification

作　　者：唐型基[1] 杨光临[1] 柴群[1] TANG Xingji;YANG Guanglin;CAI Qun(Kaili University,Kaili Guizhou 556011,China)

机构地区：[1]凯里学院,贵州凯里556011

出　　处：《长江信息通信》2024年第12期61-63,共3页Changjiang Information & Communications

基　　金：贵州省第2023年“金课”;项目名称:线下一流课;项目编号:SJJK202311;贵州省高等学校教学内容和课程体系改革项目;项目名称:基于OBE理念的教学模式改革与探索—以《Java程序设计》为例;项目编号:SJG2023334;凯里学院校级课题;项目名称:“数据库原理及应用”课程教育范式改革试点项目;项目编号:FS201818。凯里学院校级课题:“‘数据库原理及应用’课程教育范式改革试点项目”(项目编号:FS201818)。

摘　　要：针对现有识别方法在对编程语言(Java Programming Language, Java)代码注入攻击漏洞识别时,存在识别准确率低的问题,文章引入机器学习,开展Java代码注入攻击漏洞识别方法设计研究。汇聚广泛且多样的Java注入语句样本,采集数据,并生成特征量。通过机器学习,实现对Java代码注入语句的判断。通过F1值和准确率,完成Java代码注入攻击漏洞识别预测。实验结果表明:研究的识别方法具备更高的识别准确率,可准确检测Java代码注入攻击漏洞问题,提高网络安全性。In response to the problem of low recognition accuracy in identifying vulnerabilities in Java programming language(Java)code injection attacks using existing recognition methods,this article introduces machine learning to conduct research on the design of Java code injection attack vulnerability recognition methods.Gather a wide and diverse sample of Java injection statements,collect data,and generate feature quantities.Through machine learning,achieve the judgment of Java code injection statements.Complete Java code injection vulnerability identification and prediction through F1 value and accuracy.The experimental results show that the research recognition method has higher recognition accuracy,can accurately detect Java code injection attack vulnerabilities,and improve network security.

关 键 词：机器学习 代码注入攻击 语句样本 漏洞 JAVA 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]