Symbiotic Federated Learning for Giant AI Threat Detection in 6G-IoT Infrastructures

The convergence of Giant AI models and Internet of Things infrastructure in 6G environments demands intelligent, privacy-aware, and scalable threat-detection solutions at the network edge, but cloud-centric architectures struggle with data privacy, communication efficiency, and interpretability. This paper proposes SymFL-GNN, a symbiotic threat-detection framework that unifies federated learning, graph neural networks, and homomorphic encryption to enable decentralized anomaly detection across distributed 6G-enabled IoT ecosystems. SymFL-GNN supports collaborative learning among IoT devices while retaining data locally, leveraging the Paillier homomorphic cryptosystem to ensure gradient-level encryption throughout training and aggregation.