Federated Learning for Distributed Threat Intelligence Sharing Across Global Cybersecurity Networks
S. Sowmiya, Sangeetha Priya Nachimuthu, Appini Narayana Rao · 2025
The rapid evolution of cyber threats necessitates innovative approaches to enhance global cybersecurity collaboration. Federated Learning (FL) has emerged as a decentralized machine learning paradigm that enables distributed threat intelligence sharing while maintaining data privacy and security. This chapter explores the application of FL for large-scale cybersecurity networks, addressing critical challenges in scalability, security, and communication efficiency. The focus is on optimizing secure aggregation techniques to enable efficient and privacy-preserving model updates across heterogeneous and resource-constrained environments. Key solutions such as hierarchical aggregation, sparse model updates, and blockchain-based enhancements are discussed to mitigate the computational and communication overheads inherent in federated systems. the chapter investigates the integration of advanced cryptographic methods, including homomorphic encryption and differential privacy, to strengthen the security of federated networks against adversarial attacks. By leveraging FL’s potential, organizations can share threat intelligence across global networks without compromising sensitive data, significantly improving real-time cyber threat detection and response. The chapter concludes by identifying future research directions for overcoming existing challenges and further optimizing federated models in cybersecurity.