International Association
for Cryptologic Research

Tremendous efforts have been made to improve the efficiency of secure Multi-Party Computation (MPC), which allows n ≥ 2 parties to jointly evaluate a target function without leaking their own private inputs. It has been confirmed by previous researchers that 3-Party Computation (3PC) and outsourcing computations to GPUs can lead to huge performance improvement of MPC in computationally intensive tasks such as Privacy-Preserving Machine Learning (PPML). A natural question to ask is whether super-linear performance gain is possible for a linear increase in resources. In this paper, we give an affirmative answer to this question. We propose Force, an extremely efficient 4PC system for PPML. To the best of our knowledge, each party in Force enjoys the least number of local computations and lowest data exchanges between parties. This is achieved by introducing a new sharing type X -share along with MPC protocols in privacy-preserving training and inference that are semi-honest secure with an honest-majority. Our contribution does not stop at theory. We also propose engineering optimizations and verify the high performance of the protocols with implementation and experiments. By comparing the results with state-of-the-art researches such as Cheetah, Piranha, CryptGPU and CrypTen, we showcase that Force is sound and extremely efficient, as it can improve the PPML performance by a factor of 2 to 1200 compared with other latest 2PC, 3PC and 4PC system