Scholarlink

In today’s digital age, the Internet is pivotal in bringing both convenience and security concerns. Individuals are vulnerable to unauthorized access and manipulation of their information by potential attackers. A notable cybersecurity threat revolves around injections, a method for introducing malicious code into web applications, creating vulnerabilities that attackers can exploit. Within the scope of this study, our attention has been directed toward a specific form of injection attack known as cross-site scripting (XSS). Following thorough research, our strategic direction involves adopting a bagging ensemble learning method for detecting XSS anomalies. The random forest classifier was employed as the chosen model in this approach. Considering all the essential comparison parameters, the proposed simulation results significantly improve the existing work.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Detection of Cross-Site Scripting Attack Using Bagging Ensemble Learning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Liaren Emani Aier,
  • Sreya Bhowmick,
  • Barasha Das,
  • Arpita Nath Boruah,
  • Mrinal Goswami

摘要

In today’s digital age, the Internet is pivotal in bringing both convenience and security concerns. Individuals are vulnerable to unauthorized access and manipulation of their information by potential attackers. A notable cybersecurity threat revolves around injections, a method for introducing malicious code into web applications, creating vulnerabilities that attackers can exploit. Within the scope of this study, our attention has been directed toward a specific form of injection attack known as cross-site scripting (XSS). Following thorough research, our strategic direction involves adopting a bagging ensemble learning method for detecting XSS anomalies. The random forest classifier was employed as the chosen model in this approach. Considering all the essential comparison parameters, the proposed simulation results significantly improve the existing work.