Scholarlink

<p>The advent of 6G networks and the rapid expansion of IoT ecosystems, particularly in energy hub (EH) networks, present significant challenges in ensuring secure and reliable communication. Among these, Distributed Denial-of-Service (DDoS) attacks pose a critical threat to the stability of IoT-enabled infrastructures. This study addresses these challenges by systematically evaluating a range of machine learning models and hybrid ensemble techniques tailored for DDoS detection in IoT-driven 6G EH networks. The performance of Random Forest (RF), Gradient Boosting (GB), Support Vector Machines (SVM), Decision Trees (DT), and K-Nearest Neighbors (KNN), as well as hybrid combinations like RF + KNN, GB + KNN, and GB + DT, was rigorously assessed across three benchmark datasets (CICDDOS2019, KDD-CUP, and UNSW-NB) with varying training data sizes (80% and 60%). Among these, RF + KNN emerged as the most effective, achieving the highest accuracy (99.44%) and F1-score (66.62%) on CICDDOS2019 while maintaining robust performance on UNSW-NB. GB + DT demonstrated superior precision (70.95%) on KDD-CUP, while GB + KNN achieved the highest recall (66.67%) on CICDDOS2019, highlighting its capability to minimize false negatives. The findings emphasize the influence of dataset characteristics and training sizes on model performance. CICDDOS2019 consistently produced the highest accuracy due to its well-defined class separability, while KDD-CUP exhibited greater variability and UNSW-NB provided stable yet moderate precision and recall. Smaller training data sizes generally led to performance degradation in F1-score and recall, although occasional accuracy improvements suggested potential overfitting with larger datasets. This research underscores the importance of tailoring hybrid ensemble models to the specific properties of datasets and attack types, offering a scalable, real-time framework for intrusion detection. By enhancing the security and resilience of IoT-driven 6G EH networks, this study provides practical solutions to mitigate the evolving threats posed by DDoS attacks.</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

Detecting DDoS threats in IoT-driven 6G-energy hubs networks using machine learning algorithms

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年8月27日

查看全文
  • Hesham A. Sakr,
  • M. I. El-Afifi,
  • M. A. El-Mowafy,
  • H. M. Ibrahim

摘要

The advent of 6G networks and the rapid expansion of IoT ecosystems, particularly in energy hub (EH) networks, present significant challenges in ensuring secure and reliable communication. Among these, Distributed Denial-of-Service (DDoS) attacks pose a critical threat to the stability of IoT-enabled infrastructures. This study addresses these challenges by systematically evaluating a range of machine learning models and hybrid ensemble techniques tailored for DDoS detection in IoT-driven 6G EH networks. The performance of Random Forest (RF), Gradient Boosting (GB), Support Vector Machines (SVM), Decision Trees (DT), and K-Nearest Neighbors (KNN), as well as hybrid combinations like RF + KNN, GB + KNN, and GB + DT, was rigorously assessed across three benchmark datasets (CICDDOS2019, KDD-CUP, and UNSW-NB) with varying training data sizes (80% and 60%). Among these, RF + KNN emerged as the most effective, achieving the highest accuracy (99.44%) and F1-score (66.62%) on CICDDOS2019 while maintaining robust performance on UNSW-NB. GB + DT demonstrated superior precision (70.95%) on KDD-CUP, while GB + KNN achieved the highest recall (66.67%) on CICDDOS2019, highlighting its capability to minimize false negatives. The findings emphasize the influence of dataset characteristics and training sizes on model performance. CICDDOS2019 consistently produced the highest accuracy due to its well-defined class separability, while KDD-CUP exhibited greater variability and UNSW-NB provided stable yet moderate precision and recall. Smaller training data sizes generally led to performance degradation in F1-score and recall, although occasional accuracy improvements suggested potential overfitting with larger datasets. This research underscores the importance of tailoring hybrid ensemble models to the specific properties of datasets and attack types, offering a scalable, real-time framework for intrusion detection. By enhancing the security and resilience of IoT-driven 6G EH networks, this study provides practical solutions to mitigate the evolving threats posed by DDoS attacks.