Paper 2023/1890

Lightning Fast Secure Comparison for 3PC PPML

Abstract

Privacy-preserving machine learning (PPML) techniques have gained significant popularity in the past years. Those protocols have been widely adopted in many real-world security-sensitive machine-learning scenarios. Secure comparison is one of the most important non-linear operations in PPML. In this work, we focus on maliciously secure comparison in the 3-party MPC over ring $\mathbb{Z}_{2^\ell}$ setting. In particular, we propose a novel 2-round sign-bit extraction protocol in the preprocessing model. The communication of its semi-honest version is only 25\% of the state-of-the-art (SOTA) constant-round semi-honest comparison protocol by Zhou et al. (Bicoptor, S\&P 2023); communication and round complexity of its malicious version are approximately 25\% and 50\% respectively of the SOTA by Patra and Suresh (BLAZE, NDSS 2020), for $\ell=64$. Finally, the resulting ReLU protocol outperforms the SOTA secure ReLU evaluation solution (Bicoptor, S\&P 2023) by $3\times$ in the semi-honest setting and $3\times$ in the malicious setting, respectively.