Meteor: Improved Secure 3-Party Neural Network Inference with Reducing Online Communication Costs

ePrint Report: Meteor: Improved Secure 3-Party Neural Network Inference with Reducing Online Communication Costs

Ye Dong, Xiaojun Chen, Weizhan Jing, Kaiyun Li, Weiping Wang

Secure neural network inference has been a promising solution to private Deep-Learning-as-a-Service, which enables the service provider and user to execute neural network inference without revealing their private inputs. However, the expensive overhead of current schemes is still an obstacle when applied in real applications. In this work, we present \textsc{Meteor}, an online communication-efficient and fast …

as-a-service chen communication current eprint report inputs meteor network neural network party private report service service provider solution