PolyDNN: Polynomial Representation of NN for Communication-less SMPC Inference

TL;DR

This paper introduces PolyDNN, a method to translate deep neural networks into polynomials for secure multi-party computation, enabling communication-less inference and protecting model information.

Contribution

It presents a novel approach to convert entire neural networks into polynomials for efficient, communication-free secure inference using MPC techniques.

Findings

Complete networks can be translated into a single polynomial.

The polynomial can be computed securely without intermediate communication.

The method enhances privacy and efficiency in secure neural network inference.

Abstract

The structure and weights of Deep Neural Networks (DNN) typically encode and contain very valuable information about the dataset that was used to train the network. One way to protect this information when DNN is published is to perform an interference of the network using secure multi-party computations (MPC). In this paper, we suggest a translation of deep neural networks to polynomials, which are easier to calculate efficiently with MPC techniques. We show a way to translate complete networks into a single polynomial and how to calculate the polynomial with an efficient and information-secure MPC algorithm. The calculation is done without intermediate communication between the participating parties, which is beneficial in several cases, as explained in the paper.