The overhead of non-linear functions dominates the performance of the secure multiparty computation (MPC) based privacy-preserving machine learning (PPML). This work introduces a family of novel secure three-party computation (3PC) protocols, Bicoptor, which improve the efficiency of evaluating non-linear functions. The basis of Bicoptor is a new sign determination protocol, which relies on a clever use of the truncation protocol proposed in SecureML (S\&P 2017). Our 3PC sign determination protocol only requires two communication rounds, and does not involve any preprocessing. Such sign determination protocol is well-suited for computing non-linear functions in PPML, e.g. the activation function ReLU, Maxpool, and their variants. We develop suitable protocols for these non-linear functions, which form a family of GPU-friendly protocols, Bicoptor. All Bicoptor protocols only require two communication rounds without preprocessing. We evaluate Bicoptor under a 3-party LAN network over a public cloud, and achieve more than 370,000 DReLU/ReLU or 41,000 Maxpool (find the maximum value of nine inputs) operations per second. Under the same settings and environment, our ReLU protocol has a one or even two orders of magnitude improvement to the state-of-the-art works, Falcon (PETS 2021) or Edabits (CRYPTO 2020), respectively without batch processing.

翻译：非线性函数的开销主导了基于安全多方计算（MPC）的隐私保护机器学习（PPML）的性能。本文提出一类新型安全三方计算（3PC）协议族Bicoptor，旨在提升非线性函数评估效率。Bicoptor的核心是一个新的符号判定协议，该协议巧妙利用了SecureML（S&P 2017）中提出的截断协议。我们的3PC符号判定协议仅需两轮通信，且无需任何预处理。该符号判定协议非常适合计算PPML中的非线性函数，例如激活函数ReLU、Maxpool及其变体。我们为这些非线性函数开发了合适的协议，形成了Bicoptor这一GPU友好型协议族。所有Bicoptor协议均仅需两轮通信且无需预处理。我们在公有云的三方局域网环境下评估Bicoptor，每秒可执行超过370,000次DReLU/ReLU运算或41,000次Maxpool（在九个输入中寻找最大值）运算。在相同设置和环境下，与最先进的Falcon（PETS 2021）或Edabits（CRYPTO 2020）相比，我们的ReLU协议在无批处理情况下分别实现了一到两个数量级的性能提升。