We propose differentially private algorithm for non-convex empirical risk minimization with reduced gradient complexity.
We combine differential privacy and MPC for privacy preserving distributed learing of strongly-convex ERM algorithms.
We use MPC to allow certificate authorities to sign digital certificates in a secure and distributed way.
Allowing certificate authorities to sign digital certificates in a secure and distributed way.
We use MPC to aggregate models in a private and distributed way.
Combining differential privacy and multi-party computation techniques for private machine learning.