Accurate nonlinear computation is a key challenge in privacy-preserving machine learning (PPML). Most existing frameworks approximate it through linear operations, resulting in significant precision loss. This paper proposes an efficient, verifiable and accurate security 2-party logistic regression framework (EVA-S2PLoR), which achieves accurate nonlinear function computation through a novel secure element-wise multiplication protocol and its derived protocols. Our framework primarily includes secure 2-party vector element-wise multiplication, addition to multiplication, reciprocal, and sigmoid function based on data disguising technology, where high efficiency and accuracy are guaranteed by the simple computation flow based on the real number domain and the few number of fixed communication rounds. We provide secure and robust anomaly detection through dimension transformation and Monte Carlo methods. EVA-S2PLoR outperforms many advanced frameworks in terms of precision (improving the performance of the sigmoid function by about 10 orders of magnitude compared to most frameworks) and delivers the best overall performance in secure logistic regression experiments.

翻译：精确的非线性计算是隐私保护机器学习（PPML）中的一个关键挑战。大多数现有框架通过线性运算对其进行近似，导致显著的精度损失。本文提出了一种高效、可验证且精确的安全两方逻辑回归框架（EVA-S2PLoR），该框架通过一种新颖的安全逐元素乘法协议及其衍生协议，实现了精确的非线性函数计算。我们的框架主要包括基于数据伪装技术的安全两方向量逐元素乘法、加法转乘法、倒数以及Sigmoid函数计算，其中基于实数域的简单计算流程和少量的固定通信轮次保证了高效率和准确性。我们通过维度变换和蒙特卡洛方法提供了安全且鲁棒的异常检测。EVA-S2PLoR在精度方面优于许多先进框架（与大多数框架相比，其Sigmoid函数的性能提升了约10个数量级），并在安全逻辑回归实验中实现了最佳的综合性能。