Sphynx: ReLU-Efficient Network Design for Private Inference

Understand

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.