Paper 2023/493

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

Tianxiang Dai, Huawei Technologies (Germany)
Li Duan, Huawei Technologies (Germany)
Yufan Jiang, Huawei Technologies (Germany)
Yong Li, Huawei Technologies (Germany)
Fei Mei, Huawei Technologies (Germany)
Yulian Sun, Huawei Technologies (Germany)

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 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 Force, an extremely efficient Four-Party Computation (4PC) system for PPML. To the best of our knowledge, each party in 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 X-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 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 Piranha (including SecureML, Falcon, FantasticFour), CryptGPU and CrypTen.

Available format(s)
Cryptographic protocols
Publication info
Published elsewhere. Nordsec 2023
MPCprivacy-preserving machine learningFour-party computation
Contact author(s)
yufan jiang @ huawei com
yong li1 @ huawei com
2023-11-06: last of 3 revisions
2023-04-04: received
See all versions
Short URL
Creative Commons Attribution


      author = {Tianxiang Dai and Li Duan and Yufan Jiang and Yong Li and Fei Mei and Yulian Sun},
      title = {Force: Highly Efficient Four-Party Privacy-Preserving Machine Learning on {GPU}},
      howpublished = {Cryptology ePrint Archive, Paper 2023/493},
      year = {2023},
      note = {\url{}},
      url = {}
Note: In order to protect the privacy of readers, does not use cookies or embedded third party content.