摘要
随着WEB应用程序的普及,对其安全性的关注日益增加。漏洞检测作为保障WEB应用程序安全的关键手段之一备受重视。本文综合了多种漏洞检测方法,提出了基于机器学习算法的WEB应用程序漏洞检测策略。通过结合敏感性分析、静态信息流跟踪和双向数据流分析等步骤,本文设计了一个综合性的漏洞检测方法,并在测试环境下取得了98%准确率的优异表现。
With the popularity of WEB applications,concerns about their security have increased.Vulnerability detection,as one of the key means to ensure the security of WEB applications,has been highly valued.This article combines a variety of vulnerability detection methods and proposes a machine learning-based strategy for WEB application vulnerability detection.By integrating sensitivity analysis,static information flow tracking,and bidirectional data flow analysis,this article designs a comprehensive vulnerability detection method,which has achieved an excellent performance with an accuracy rate of 98%in the test environment.
作者
王彬
蒋铭初
周进
李晓禹
陈泽翰
Wang Bin;Jiang Mingchu;Zhou Jin;Li Xiaoyu;Chen Zehan(The 28th Research Institute of China Electronics Technology Group Corporation,Nanjing,China)
出处
《科学技术创新》
2025年第15期83-86,共4页
Scientific and Technological Innovation
关键词
支持向量机
漏洞扫描
检测策略
SVM
vulnerability scanning
detection strategy
作者简介
王彬(1990-),男,硕士研究生,工程师,研究方向:网络信息安全。
