Scholarlink

In today’s world, network attacks are a major security concern due to the fast-paced progress of the internet and technology. DoS attacks are complex threats that are hard to combat. Distributed Denial of Service (DDoS) attacks are even more hazardous as they can cause significant disruptions. Furthermore, they are particularly challenging because they can strike unexpectedly and quickly cripple a victim’s communication or computing resources. DDoS attacks are a constantly evolving threat which is increasingly challenging to detect and effectively mitigate. To counter this menace, we have explored diverse techniques and methods on the DDoS attack dataset, i.e., SDN-specific dataset. Machine learning has improved DDoS detection by implementing various algorithms, including decision trees, support vector machine, Naive Bayes, K-Nearest Neighbor, MultiLayer Perceptron, Quadratic Discriminant, Stochastic Gradient Descent (SGD), Logistic Regression, XGBoost, and deep learning methodologies such as Deep Neural Networks (DNN). An extensive comparative analysis of these algorithms has evaluated their performance based on accuracy metrics.

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

Cybersecurity Threat Detection of Anomaly-Based DDoS Attack Using Machine Learning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Jyoti Neeli,
  • S. Vijaya Shetty,
  • M. Anjali,
  • Shamshekhar S. Patil

摘要

In today’s world, network attacks are a major security concern due to the fast-paced progress of the internet and technology. DoS attacks are complex threats that are hard to combat. Distributed Denial of Service (DDoS) attacks are even more hazardous as they can cause significant disruptions. Furthermore, they are particularly challenging because they can strike unexpectedly and quickly cripple a victim’s communication or computing resources. DDoS attacks are a constantly evolving threat which is increasingly challenging to detect and effectively mitigate. To counter this menace, we have explored diverse techniques and methods on the DDoS attack dataset, i.e., SDN-specific dataset. Machine learning has improved DDoS detection by implementing various algorithms, including decision trees, support vector machine, Naive Bayes, K-Nearest Neighbor, MultiLayer Perceptron, Quadratic Discriminant, Stochastic Gradient Descent (SGD), Logistic Regression, XGBoost, and deep learning methodologies such as Deep Neural Networks (DNN). An extensive comparative analysis of these algorithms has evaluated their performance based on accuracy metrics.