Provably secure federated learning with ECCDH-based group key agreement for enhanced privacy in collaborative model training

Abstract

Federated Learning (FL) facilitates collaborative training of models without exchanging any data, thereby ensuring data locality. However, the exchange of local model updates is still susceptible to attacks such as gradient inference, model reconstruction, man-in-the-middle, replay, and tampering, which create considerable privacy and security concerns. In this paper, we propose a framework for secure federated learning by combining a decentralized group key establishment scheme using ECCDH, SHA-256 based key derivation, cryptographically secure PRNG-based additive masking, and ECDSA authentication for protecting local model updates in a collaborative training process. While existing schemes require key management infrastructure, trusted third parties, or homomorphic/hyperencryption/multi-party computation techniques, our scheme allows clients to establish a common cryptographic seed in a collaborative fashion.The derived seeds are converted into synchronized masking vectors through the utilization of a secure PRNG, enabling the clients to mask their local models' updates while still maintaining compatibility with the standard FedAvg aggregation algorithm. Additionally, the use of SHA-256 and ECDSA guarantees message integrity, client authentication, and replay protection before performing the aggregation process. The formal security model and theorem prove the security properties of confidentiality, integrity, authentication, replay resistance, forward secrecy, and collusion resistance of the proposed scheme under the probabilistic polynomial-time (PPT) adversary under the hardness assumption of the ECDLP and CDH problems. The experimental study performed on five benchmark data sets (i.e., Iris, Breast Cancer, Wine, Diabetes, and Prostate Cancer) shows that the proposed framework maintains similar predictive performance as the conventional federated learning while incurring minimal overhead costs. Hence, the findings show that the proposed ECCDH-based secure aggregation framework provides an efficient and scalable way of federated learning without the use of any trusted third party.