Experiment Parameter Comparison for SD-WAN DDoS Attack Detection

A dataset collected by Mohamed Musa during experiments to train and test a machine learning model for detecting DDoS attacks in SDN-enabled SD-WAN networks. The dataset is stored in an XLS file sized 5.5 KB and was last updated on May 12, 2026. It was used to develop an adaptive model integrating RF and DT algorithms, achieving up to 99.97% accuracy.

Use Cases

• Training machine learning models for DDoS attack detection based on SD-WAN network traffic features.
• Comparing the performance of Random Forest (RF) and Decision Tree (DT) algorithms for network security tasks.
• Testing preprocessing pipelines like QT-PCA for dimensionality reduction on network event data.
• Evaluating dynamic, event-triggered mitigation strategies for PACKET_IN events in SDN controllers.

Strengths

• Model performance metrics are reported with high precision, achieving 99.97% accuracy for high-rate attacks and 99.96% for low-rate attacks.
• The dataset is openly licensed under CC-BY-4.0, facilitating reuse and sharing.
• The description details a specific methodological pipeline involving QT-PCA preprocessing and PACKET_IN event-triggered mitigation.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small at 5.5 KB, indicating limited scope.

Provenance

Source

Mohamed Musa via figshare

Collection Method

Collected during controlled experiments on SD-WAN security.

Freshness

Last updated 2026-05-12 17:37:29; freshness should be verified.