English

Sphynx: ReLU-Efficient Network Design for Private Inference

Cryptography and Security 2022-11-08 v1 Machine Learning

Abstract

The emergence of deep learning has been accompanied by privacy concerns surrounding users' data and service providers' models. We focus on private inference (PI), where the goal is to perform inference on a user's data sample using a service provider's model. Existing PI methods for deep networks enable cryptographically secure inference with little drop in functionality; however, they incur severe latency costs, primarily caused by non-linear network operations (such as ReLUs). This paper presents Sphynx, a ReLU-efficient network design method based on micro-search strategies for convolutional cell design. Sphynx achieves Pareto dominance over all existing private inference methods on CIFAR-100. We also design large-scale networks that support cryptographically private inference on Tiny-ImageNet and ImageNet.

Keywords

Cite

@article{arxiv.2106.11755,
  title  = {Sphynx: ReLU-Efficient Network Design for Private Inference},
  author = {Minsu Cho and Zahra Ghodsi and Brandon Reagen and Siddharth Garg and Chinmay Hegde},
  journal= {arXiv preprint arXiv:2106.11755},
  year   = {2022}
}
R2 v1 2026-06-24T03:28:04.111Z