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.
翻译:联邦学习可能同时受到全球聚合攻击和分布式中毒攻击; 已经建议采用链式技术以及奖励和惩罚机制来对付这些攻击; 在本文中,我们探讨利用零知识证明来替代基于链式联合学习的奖励和惩罚机制的可核查的离链式计算方法; 在我们的解决方案中,学习节点,除了其计算义务外,还作为非链式验证人,提交证明可在链式链式中核实的参数的计算正确性的证据; 我们通过健康监测使用案例和概念验证实施,利用ZoKrates的语言和工具进行智能合同式链式管理,来展示和评价我们的解决方案。 我们的研究引入了学习过程正确性的可核查性,从而推进了基于链式联合学习。