This paper identifies network topology as a fundamental privacy vulnerability in federated learning systems, demonstrating that adversaries can infer sensitive data distribution patterns through communication patterns, parameter magnitudes, and structural correlations even under strong differential privacy guarantees.

This paper proposes TrustMesh, a novel blockchain-enabled framework that addresses these challenges through a unique three-layer architecture combining permissioned blockchain technology with a novel multi-phase Practical Byzantine Fault Tolerance (PBFT) consensus protocol.