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.

中文翻译：

---

Voltran：在去中心化联邦学习聚合中解锁信任和机密性


基于区块链架构构建的去中心化联邦学习 （FL） 范式利用分布式节点集群来取代执行 FL 模型聚合的单个服务器。这种范式解决了 vanilla FL 中中心化恶意服务器的漏洞，并继承了区块链提供的可信性和健壮性。然而，现有的区块链支持方案面临着与模型机密性不足和区块链计算资源有限相关的挑战。在本文中，我们介绍了 Voltran，这是一个创新的混合平台，旨在基于可信执行环境 （TEE） 和区块链技术的组合实现 FL 的信任、机密性和稳健性。我们将 FL 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，然后保证区块链上聚合结果的真实性和可验证性。此外，我们通过引入多 SGX 并行执行策略来分摊大规模 FL 工作负载，从而在多个 FL 场景中提供强大的可扩展性。我们实施了 Voltran 的原型并进行了全面的性能评估。广泛的实验结果表明，Voltran 在保证信任、机密性和真实性的同时，产生的额外开销最小，与最先进的密文聚合方案相比，它显着提高了速度。