OptiPrime: Optimizing Private Inference through Protocol-Hardware Co-design
Private deep neural network (DNN) inference based on hybrid homomorphic encryption (HE) and multi-party computation (MPC) can protect user data with a formal guarantee, but at the cost of significant latency overhead due to HE. Customized HE accelerators have been proposed and have achieved orders-of-magnitude speedup...
Jiang-Rui Yu, Ye Yu, Si Chen et al.
· 0 citations