arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.02554cs.AIcs.CRcs.LG
收藏

zkFL:基于零知识证明的联邦学习梯度聚合

zkFL: Zero-Knowledge Proof-based Gradient Aggregation for Federated Learning

Department of Computing, Imperial College London(帝国理工学院 computing 部);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Department of Computer Science and Engineering, Hong Kong University of Science and Technology(香港科学与技术大学计算机科学与工程系)

Zhipeng Wang, Nanqing Dong, Jiahao Sun, William Knottenbelt, Yike Guo

AI总结:

本文提出zkFL框架,利用零知识证明和区块链验证机制抵御联邦学习中的恶意聚合器攻击,在不改变网络结构的前提下提升安全性与隐私性。

摘要:

联邦学习(FL)是一种机器学习范式,它使多个去中心化的客户端能够在中央聚合器的协调下协作训练模型。在大数据场景中,FL可以成为一种可扩展的机器学习解决方案。传统FL依赖于中央聚合器的信任假设,即聚合器诚实地组建客户端群组。然而,在现实中,恶意聚合器可能会丢弃并替换客户端的训练模型,或插入虚假客户端,以操纵最终训练结果。在这项工作中,我们提出了zkFL,它利用零知识证明来解决训练模型聚合过程中恶意聚合器的问题。为了保证聚合结果的正确性,聚合器在每一轮都提供一个证明,向客户端证明聚合器忠实地执行了预期的行为。为了进一步降低客户端的验证成本,我们使用区块链以零知识的方式处理证明,其中矿工(即验证和维护区块链数据的参与者)可以在不知道客户端本地模型和聚合模型的情况下验证证明。理论分析和实验结果表明,zkFL在不修改底层FL网络结构或严重损害训练速度的情况下,实现了比传统FL更好的安全性和隐私性。

英文摘要:

Federated learning (FL) is a machine learning paradigm, which enables multiple and decentralized clients to collaboratively train a model under the orchestration of a central aggregator. FL can be a scalable machine learning solution in big data scenarios. Traditional FL relies on the trust assumption of the central aggregator, which forms cohorts of clients honestly. However, a malicious aggregator, in reality, could abandon and replace the client's training models, or insert fake clients, to manipulate the final training results. In this work, we introduce zkFL, which leverages zero-knowledge proofs to tackle the issue of a malicious aggregator during the training model aggregation process. To guarantee the correct aggregation results, the aggregator provides a proof per round, demonstrating to the clients that the aggregator executes the intended behavior faithfully. To further reduce the verification cost of clients, we use blockchain to handle the proof in a zero-knowledge way, where miners (i.e., the participants validating and maintaining the blockchain data) can verify the proof without knowing the clients' local and aggregated models. The theoretical analysis and empirical results show that zkFL achieves better security and privacy than traditional FL, without modifying the underlying FL network structure or heavily compromising the training speed.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑