Training Differentially Private Models with Secure Multiparty Computation. (arXiv:2202.02625v3 [cs.CR] UPDATED)

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 …

computation secure multiparty computation training