Federated Learning for Collaborative Network Security in Decentralized Environments
Bheema Shanker Neyigapula · Research Square · 2023
Abstract In decentralized network environments, collaborative efforts are crucial to bol- stering network security against ever-evolving threats from malicious actors. Federated Learning has emerged as a promising solution, enabling multiple nodes to collectively train machine learning models while preserving data privacy. This research proposes SentinelNet, a novel Federated Learning framework specif- ically designed for collaborative network security. The framework emphasizes secure threat intelligence sharing, privacy-preserving techniques, and adaptive learning mechanisms. Through comprehensive evaluations and real-world case studies, SentinelNet demonstrates its efficacy in enhancing network security while maintaining data confidentiality. The research highlights the significance of col- laborative approaches and advocates the adoption of Federated Learning to fortify decentralized network ecosystems.