Scholarlink

Risks to network data safety are currently increasing rapidly in both number and severity. Hackers nowadays usually take advantage of people’s vulnerabilities and end-to-end technologies. These tactics include, among others, social engineering, pharming, and phishing. One step in these assaults is to deceive people by utilizing misleading URLs. Fraudulent URL authentication is therefore crucial at the moment. Several scholarly articles have addressed the use of machine learning to identify misleading URLs. With respect to our suggested URL patterns and features, this publication recommends a machine learning (ML) depending on technique for detecting unauthorized URLs. In this case, URLs are classified using the Random Forest as well as multinomial Naive Bayes classifiers; the associated classification accuracy rates are 97.33% for Decision Tree, 96.19% for Multinomial Naïve Bayes, and 97% for Random Forest.

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

Exploration into the Analysis and Identification of Phishing URLs in Emails Using Machine Learning Techniques

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • B. Gayathri,
  • M. Anusha Reddy,
  • G. Prisilla Jayanthi,
  • Ravi Kumar Chandu,
  • S. Pournima

摘要

Risks to network data safety are currently increasing rapidly in both number and severity. Hackers nowadays usually take advantage of people’s vulnerabilities and end-to-end technologies. These tactics include, among others, social engineering, pharming, and phishing. One step in these assaults is to deceive people by utilizing misleading URLs. Fraudulent URL authentication is therefore crucial at the moment. Several scholarly articles have addressed the use of machine learning to identify misleading URLs. With respect to our suggested URL patterns and features, this publication recommends a machine learning (ML) depending on technique for detecting unauthorized URLs. In this case, URLs are classified using the Random Forest as well as multinomial Naive Bayes classifiers; the associated classification accuracy rates are 97.33% for Decision Tree, 96.19% for Multinomial Naïve Bayes, and 97% for Random Forest.