# Sphynx: ReLU-Efficient Network Design for Private Inference Source: [Sphynx: ReLU-Efficient Network Design for Private Inference]() Collection index: [llms.txt]() Data updated: 2025-10-26T00:44:11.594Z Authors: Minsu Cho, Zahra Ghodsi, Brandon Reagen, Siddharth Garg, Chinmay Hegde Published: 2021-06-17T18:11:10.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()