An Intelligent Framework for Zero-Day Ddos Attack Detection in Sdn Federated Learning Environments

1r Rajakumar, 2nadiminti Chaithanya Lakshmi, 3muniramannagari Lahari,4tippagalla Jaswanth,5kethaMadhan
1Assistant Professor,Department of Information Technology, SV college of Engineering, Tirupati, India
2B.Tech, Department of Information Technology, SV college of Engineering, Tirupati, India
3B.Tech, Department of Information Technology, SV college of Engineering, Tirupati, India
4B.Tech, Department of Information Technology, SV college of Engineering, Tirupati, India
5B.Tech, Department of Information Technology, SV college of Engineering, Tirupati, India
.Email: rajakumar.r@svce.edu.in, nadimintichaithanyalakshmi06@gmail com, lariyadav311@gmail.com,
jaswanthraj080100@gmail.com, madhanketha@gmail.com
Corresponding Author/Guide: R Raja Kumar, M.tech(Ph.D), Assistant Professor

ABSTRACT:A Distributed Denial of Service (DDoS) attack is a malicious attempt to overwhelm a targeted system or network by flooding it with traffic from multiple compromised devices, causing disruption or denial of service to legitimate users. This paper addresses the critical challenge of detecting Distributed Denial of Service (DDoS) attacks in Software-Defined Networking (SDN)-assisted Federated Learning (FL) environments. Existing DDoS detection systems using hybrid LSTM SVM and CNN-BiGRU contrastive learning deliver high accuracy but face key limitations: they require substantial computational resources, show limited adaptability to evolving and complex network environments, and depend on offline training with simulated data, which limits real-time deployment in dynamic large-scale networks. The proposed system enhances DDoS attack detection by integrating real-time monitoring, adaptive model updating, and deployment in livenetwork environments. It employs continuous model parameter optimization via an accuracy comparator and multi dimensional feature extraction to effectively detect zero-day and low-rate attacks. This real-time adaptability improves robustness against evolving threats and complex networks. Benefits include higher detection accuracy, scalability in resource-limited environments, better identification of novel attacks, and reduced false positives/negatives, thereby strengthening security and reliability in SDN-assisted Federated Learning networks.
KEYWORDS: Distributed Denial of Service (DDoS), Software-Defined Networking (SDN), Contrastive learning, Parameter Optimization, Real-time monitoring, Federated Learning