Efficient Secure Aggregation Based on SHPRG For Federated Learning
Efficient Secure Aggregation Based on SHPRG For Federated Learning
We propose a novel secure aggregation scheme based on seed-homomorphic pseudo-random generator (SHPRG) to prevent private training data leakage from model-related information in Federated Learning systems. Our constructions leverage the homomorphic property of SHPRG to simplify the masking and demasking scheme, which entails a linear overhead while revealing nothing beyond …