基于RASP和机器学习的SQL注入检测方法  

Detection of SQL injection based on RASP and machine learning

作  者:秦泽坤 聂闻 董林旺 骆明华 QIN Ze-kun;NIE Wen;DONG Lin-wang;LUO Ming-hua(College of Mechanical and Electrical Engineering,Fujian Agriculture and Forestry University,Fuzhou 350100,China;Quanzhou Institute of Equipment Manufacturing,Haixi Institutes,Chinese Academy of Sciences,Quanzhou 362000,Fujian Province,China;College of Resources and Environmental Engineering,Jiangxi University of Science and Technology,Ganzhou 341000,Jiangxi Province,China)

机构地区:[1]福建农林大学机电工程学院,福州350100 [2]中国科学院海西研究院泉州装备制造研究中心,福建泉州362000 [3]江西理工大学资源与环境工程学院,江西赣州341000

出  处:《信息技术》2025年第3期69-75,85,共8页Information Technology

基  金:福建省科学院科学技术合作计划(STS,2022T3051);江西省杰出青年基金(20212ACB214005)。

摘  要:为了在DevOps环境下对Web应用的SQL注入进行有效防御,针对目前检测SQL注入方法中的问题,提出了一种基于RASP(Runtime Application Self-Protection,运行时应用自我保护)和机器学习的SQL注入检测方法。使用RASP技术通过监控应用程序的执行过程,在攻击发生时及时识别并阻止恶意SQL语句的执行,通过结合机器学习算法来对SQL注入攻击进行自动化识别和分类,对输入的SQL语句是否包含恶意注入代码进行准确的判断。实验表明,成功拦截了SQLMAP等级三发送的225条SQL注入请求中的219条攻击语句,证明该方案能够在不修改所防护应用程序的源码的情况下实现对SQL注入攻击的有效判断识别和拦截。In order to effectively defend against SQL injection attacks and improve the security of Web applications under DevOps environment.This paper proposed a method of SQL injection detection based on RASP(Runtime Application Self-Protection)and machine learning.RASP technology is used to identify and block the execution of malicious SQL statements when an attack occurrs by monitoring the execution of the application.By combining the machine learning algorithm,the SQL injection attacks are automatically identified and classified,whether the input SQL statement contains malicious injection code is accurately judged.The experiment shows that among 225 SQL injection requests sent by SQLMAP level 3,219 attack statements are successfully intercepted.This scheme can realize effective identification and interception of SQL injection attacks without modifying the source code of protected application.

关 键 词:SQL注入攻击 运行时应用自我保护 ALBERT 逻辑回归 DevSecOps 

分 类 号:TP311.5[自动化与计算机技术—计算机软件与理论]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象