Advancing Blockchain-based Federated Learning through Verifiable Off-chain Computations

TL;DR

This paper proposes using zero-knowledge proofs for verifiable off-chain computations in blockchain-based federated learning, enhancing security and correctness without relying solely on incentive mechanisms.

Contribution

It introduces a novel approach employing zero-knowledge proofs for verifiable off-chain computations, improving trustworthiness in blockchain federated learning.

Findings

Demonstrated feasibility through a health monitoring case study.

Implemented a proof-of-concept using ZoKrates tools.

Showed improved verifiability of learning processes.

Abstract

Federated learning may be subject to both global aggregation attacks and distributed poisoning attacks. Blockchain technology along with incentive and penalty mechanisms have been suggested to counter these. In this paper, we explore verifiable off-chain computations using zero-knowledge proofs as an alternative to incentive and penalty mechanisms in blockchain-based federated learning. In our solution, learning nodes, in addition to their computational duties, act as off-chain provers submitting proofs to attest computational correctness of parameters that can be verified on the blockchain. We demonstrate and evaluate our solution through a health monitoring use case and proof-of-concept implementation leveraging the ZoKrates language and tools for smart contract-based on-chain model management. Our research introduces verifiability of correctness of learning processes, thus advancing blockchain-based federated learning.