Scholarlink

<p>In the current era, network environments are essential for human survival but are susceptible to multiple threats like DDoS, phishing, ransomware, and SQL injection, which endanger individuals and organizations. DDoS attacks disrupt service by flooding networks with traffic from various sources, necessitating robust detection methods. While considerable research has utilized machine learning (ML) for attack detection, optimal features and techniques remain undetermined. This paper employs ML methods including artificial neural networks, decision tables, naive Bayes, support vector machines, and ensemble bagging to identify and evaluate novel DDoS detection features. Using datasets such as CICDDoS2019, UNSW-NB15, NSL-KDD, and SDN, the proposed model achieves accuracies of 96.13%, 99.63%, and 99.77% respectively.</p>

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

A Machine Learning-Based Automated DDoS Malware Attack Detection Scheme

  • 期刊论文

  • 发表日期：

    2026年4月9日

查看全文
  • Shivam Patidar,
  • Samayveer Singh,
  • Aruna Malik

摘要

In the current era, network environments are essential for human survival but are susceptible to multiple threats like DDoS, phishing, ransomware, and SQL injection, which endanger individuals and organizations. DDoS attacks disrupt service by flooding networks with traffic from various sources, necessitating robust detection methods. While considerable research has utilized machine learning (ML) for attack detection, optimal features and techniques remain undetermined. This paper employs ML methods including artificial neural networks, decision tables, naive Bayes, support vector machines, and ensemble bagging to identify and evaluate novel DDoS detection features. Using datasets such as CICDDoS2019, UNSW-NB15, NSL-KDD, and SDN, the proposed model achieves accuracies of 96.13%, 99.63%, and 99.77% respectively.