Scholarlink

The impact that the COVID-19 pandemic has had on the use of online services is undeniable. The need to move to a work-from-home model has led to greater adoption of collaborative work technologies, especially video conferencing. At the same time, the closure of entertainment establishments increased the search for video games and video streaming services, contributing to the growth of technological dependence. It is in this scenario, in which the use of the internet becomes essential to everyday life, that attacks aimed at rendering services unusable become increasingly frequent. The diversity of attack types, along with the inability to predict their occurrence, makes detecting attacks and mitigating their severity a challenge. This work aims to analyze the performance of machine learning techniques for detecting DDoS attacks in cloud computers, using network training to differentiate normal traffic from anomalous traffic. To achieve this, tests will be carried out with different algorithms on two sets of data focusing on denial of service attacks, NSL-KDD and CiCDDoS2019.

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

DDOS Attack Detection in Cloud Computing Architecture Using Deep Learning Algorithms

  • 章节

  • 发表日期：

    2025年

查看全文
  • Lina Jamal Ibrahim,
  • Almuntadher Alwhelat,
  • Fadi Al-Turjman

摘要

The impact that the COVID-19 pandemic has had on the use of online services is undeniable. The need to move to a work-from-home model has led to greater adoption of collaborative work technologies, especially video conferencing. At the same time, the closure of entertainment establishments increased the search for video games and video streaming services, contributing to the growth of technological dependence. It is in this scenario, in which the use of the internet becomes essential to everyday life, that attacks aimed at rendering services unusable become increasingly frequent. The diversity of attack types, along with the inability to predict their occurrence, makes detecting attacks and mitigating their severity a challenge. This work aims to analyze the performance of machine learning techniques for detecting DDoS attacks in cloud computers, using network training to differentiate normal traffic from anomalous traffic. To achieve this, tests will be carried out with different algorithms on two sets of data focusing on denial of service attacks, NSL-KDD and CiCDDoS2019.