Accuracy and efficiency remain challenges for multi-party computation (MPC) frameworks. Spin is a GPU-accelerated MPC framework that supports multiple computation parties and a dishonest majority adversarial setup. We propose optimized protocols for non-linear functions that are critical for machine learning, as well as several novel optimizations specific to attention that is the fundamental unit of Transformer models, allowing Spin to perform non-trivial CNNs training and Transformer inference without sacrificing security. At the backend level, Spin leverages GPU, CPU, and RDMA-enabled smart network cards for acceleration. Comprehensive evaluations demonstrate that Spin can be up to $2\times$ faster than the state-of-the-art for deep neural network training. For inference on a Transformer model with 18.9 million parameters, our attention-specific optimizations enable Spin to achieve better efficiency, less communication, and better accuracy.

翻译：准确性和效率仍然是多方计算（MPC）框架面临的挑战。Spin是一种支持多方计算参与方和恶意多数对抗设置的GPU加速MPC框架。我们针对机器学习中关键的非线性函数提出了优化协议，并针对Transformer模型的基本单元——注意力机制——提出了多项新颖优化，使得Spin能够在无需牺牲安全性的前提下执行非平凡CNN训练和Transformer推理。在后端层面，Spin利用GPU、CPU和启用RDMA的智能网卡进行加速。综合评估表明，在深度神经网络训练中，Spin的性能可比当前最先进框架提升高达$2\times$。对于拥有1890万个参数的Transformer模型推理，我们的注意力机制特化优化使Spin实现了更高的效率、更少的通信量和更好的准确性。