Voltran: Unlocking Trust and Confidentiality in Decentralized Federated Learning Aggregation
【Author】 Wang, Hao; Cai, Yichen; Wang, Jun; Ma, Chuan; Ge, Chunpeng; Qu, Xiangmou; Zhou, Lu
【Source】IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
【影响因子】7.231
【Abstract】The decentralized Federated Learning (FL) paradigm built upon blockchain architectures leverages distributed node clusters to replace the single server for executing FL model aggregation. This paradigm tackles the vulnerability of the centralized malicious server in vanilla FL and inherits the trustfulness and robustness offered by blockchain. However, existing blockchain-enabled schemes face challenges related to inadequate confidentiality on models and limited computational resources of blockchains. In this paper, we present Voltran, an innovative hybrid platform designed to achieve trust, confidentiality, and robustness for FL based on the combination of the Trusted Execution Environment (TEE) and blockchain technology. We offload the FL aggregation computation into TEE to provide an isolated, trusted and customizable off-chain execution and then guarantee the authenticity and verifiability of aggregation results on the blockchain. Moreover, we provide strong scalability on multiple FL scenarios by introducing a multi-SGX parallel execution strategy to amortize the large-scale FL workload. We implement a prototype of Voltran and conduct a comprehensive performance evaluation. Extensive experimental results demonstrate that Voltran incurs minimal additional overhead while guaranteeing trust, confidentiality, and authenticity, and it significantly brings a significant speed-up compared to state-of-the-art ciphertext aggregation schemes.
【Keywords】Blockchains; Servers; Computational modeling; Cryptography; Codes; Software; Scalability; Data models; Throughput; Smart contracts; Federated learning; secure aggregation; privacy-preserving; blockchain; trusted execution environment
【发表时间】2024
【收录时间】2024-11-09
【文献类型】案例研究
【主题类别】
区块链技术-协同技术-联邦学习
Zach
本文提出了一种名为Voltran的创新混合平台，旨在通过结合可信执行环境（TEE）和区块链技术，为基于区块链架构的联邦学习（FL）提供信任、保密性和鲁棒性。Voltran将FL模型的聚合计算卸载到TEE中，以提供隔离、可信和可定制的链下执行环境，并在区块链上保证聚合结果的真实性和可验证性。此外，通过引入多SGX并行执行策略，Voltran在多个FL场景中实现了强大的可扩展性，以分摊大规模FL工作负载。我们实现了Voltran的原型，并进行了全面的性能评估。广泛的实验结果表明，与现有的加密文本聚合方案相比，Voltran在保证信任、保密性和真实性的同时，带来了显著的速度提升，且只产生了最小的额外开销。
回复