project and sdn-ml-ddos-mitigation
These are complementary tools that address different stages of the same SDN-based DDoS defense pipeline: SVM-based detection versus Random Forest-based detection paired with active mitigation, allowing practitioners to compare detection algorithms or combine detection and response capabilities.
About project
GAR-Project/project
DDoS attacks detection by using SVM on SDN networks.
Integrates Telegraf for metrics collection, Mininet for SDN network emulation, and InfluxDB/Grafana for time-series data storage and visualization. The system trains an SVM classifier on network traffic features to distinguish between normal and DDoS activity, with a distributed architecture separating the Ryu SDN controller from the emulated network environment. Deployment is streamlined through Vagrant-based virtualization, ensuring reproducible multi-VM setups with hping3 for traffic generation and testing.
About sdn-ml-ddos-mitigation
B1rH0ut/sdn-ml-ddos-mitigation
Real-time DDoS detection and mitigation using SDN (Ryu/OpenFlow) and Machine Learning (Random Forest). Mininet spine-leaf topology with automated flow-based attack classification and blocking.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work