Scholarlink

DDoS assaults are currently one of the most frequent and expensive threats in the rapidly changing world of cyber security. A DDoS attack happens when a single server or network is targeted by a lot of internet traffic in an attempt to overwhelm it and interfere with its normal functioning. Therefore, detecting and mitigating DDOS attacks is crucial for protecting infrastructure, reducing the risk of revenue loss, maintaining a positive reputation, and improving overall security. In this paper, we have reviewed various researches on the various machine learning models used in detecting DDOS attacks together with their performance metrics which includes precision, F1-score, and accuracy. Additionally, it explains the difficulties and potential paths for machine learning research-based systems for detecting DDoS attacks.

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 Review on Detection of Distributed Denial of Service Attacks Using Machine Learning Techniques

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Jamilu Garba Ibrahim,
  • Subrata Sahana

摘要

DDoS assaults are currently one of the most frequent and expensive threats in the rapidly changing world of cyber security. A DDoS attack happens when a single server or network is targeted by a lot of internet traffic in an attempt to overwhelm it and interfere with its normal functioning. Therefore, detecting and mitigating DDOS attacks is crucial for protecting infrastructure, reducing the risk of revenue loss, maintaining a positive reputation, and improving overall security. In this paper, we have reviewed various researches on the various machine learning models used in detecting DDOS attacks together with their performance metrics which includes precision, F1-score, and accuracy. Additionally, it explains the difficulties and potential paths for machine learning research-based systems for detecting DDoS attacks.