Force: Highly Efficient Four-Party Privacy-Preserving Machine Learning on GPU

Tremendous efforts have been made to improve the efficiency of secure Multi-Party Computation (MPC), which allows \(n \ge 2\) parties to jointly evaluate a target function without leaking their own private inputs. It has been confirmed by previous research that Three-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 \(\textsf{Force}\) , an extremely efficient Four-Party Computation (4PC) system for PPML. To the best of our knowledge, each party in \(\textsf{Force}\) enjoys the least number of local computations, smallest graphic memory consumption and lowest data exchanges between parties. This is achieved by introducing a new sharing type \(\mathcal {X}\text {-}\textsf{share} \) along with MPC protocols in privacy-preserving training and inference that are semi-honest secure in the honest-majority setting. By comparing the results with state-of-the-art research, we showcase that \(\textsf{Force}\) is sound and extremely efficient, as it can improve the PPML performance by a factor of 2 to 38 compared with other latest GPU-based semi-honest secure systems, such as \(\textsf{Piranha}\) (including \(\textsf{SecureML}\) , \(\textsf{Falcon}\) , \(\textsf{FantasticFour}\) ), \(\textsf{CryptGPU}\) and \(\textsf{CrypTen}\) .