SD-WAN DDoS Attack Features for Machine Learning Detection

5.5 KB of experimental data collected by Mohamed Musa for training and testing a machine learning model to detect DDoS attacks in SD-WAN environments. The dataset was last updated on May 12, 2026, and is shared under a CC-BY-4.0 license. It was used to develop an adaptive model achieving 99.97% accuracy for high-rate attacks and 99.96% for low-rate attacks.

Use Cases

• Training DDoS attack classifiers based on network traffic features mentioned in the description
• Evaluating machine learning models for high-rate and low-rate attack detection in SD-WAN contexts
• Testing dimensionality reduction techniques like QT-PCA on network security data
• Benchmarking adaptive security frameworks for SDN-enabled networks

Strengths

• Model performance metrics are provided, with reported accuracies of 99.97% for high-rate and 99.96% for low-rate DDoS attacks
• The description details a specific preprocessing pipeline (QT-PCA) and mitigation strategy (PACKET_IN event-triggered)
• Dataset is small (5.5 KB), facilitating quick download and initial exploration

Limitations

• Row count is unknown, which may limit suitability assessment
• Column-level documentation is absent; field semantics must be inferred after download
• Description metadata is limited; actual data quality requires manual inspection after download

Provenance

Source

Mohamed Musa via figshare

Collection Method

Collected during controlled experiments on an SD-WAN security framework

Freshness

Last updated 2026-05-12 17:37:27; freshness should be verified