Paper 2022/146

Training Differentially Private Models with Secure Multiparty Computation

Sikha Pentyala, Davis Railsback, Ricardo Maia, Rafael Dowsley, David Melanson, Anderson Nascimento, and Martine De Cock


We address the problem of learning a machine learning model from training data that originates at multiple data owners, while providing formal privacy guarantees regarding the protection of each owner's data. Existing solutions based on Differential Privacy (DP) achieve this at the cost of a drop in accuracy. Solutions based on Secure Multiparty Computation (MPC) do not incur such accuracy loss but leak information when the trained model is made publicly available. We propose an MPC solution for training DP models. Our solution relies on an MPC protocol for model training, and an MPC protocol for perturbing the trained model coefficients with Laplace noise in a privacy-preserving manner. The resulting MPC+DP approach achieves higher accuracy than a pure DP approach, while providing the same formal privacy guarantees. Our work obtained first place in the iDASH2021 Track III competition on confidential computing for secure genome analysis.

Available format(s)
Cryptographic protocols
Publication info
Preprint. MINOR revision.
Secure Multiparty ComputationDifferential PrivacyLogistic Regression
Contact author(s)
sikha @ uw edu
drail @ uw edu
ricardo menezes @ aluno unb br
rafael dowsley @ monash edu
mence40 @ uw edu
andclay @ uw edu
mdecock @ uw ed
2022-02-12: received
Short URL
Creative Commons Attribution


      author = {Sikha Pentyala and Davis Railsback and Ricardo Maia and Rafael Dowsley and David Melanson and Anderson Nascimento and Martine De Cock},
      title = {Training Differentially Private Models with Secure Multiparty Computation},
      howpublished = {Cryptology ePrint Archive, Paper 2022/146},
      year = {2022},
      note = {\url{}},
      url = {}
Note: In order to protect the privacy of readers, does not use cookies or embedded third party content.