Enhancing MOTION2NX for Efficient, Scalable and Secure Image Inference using Convolutional Neural Networks

TL;DR

This paper improves the MOTION2NX framework by introducing tensorized primitives, an efficient convolution algorithm, and a novel splitting method to enhance secure CNN inference on moderate resources.

Contribution

It provides a tensorized implementation of primitives, an optimized convolution algorithm, and a new splitting technique for better efficiency and scalability in secure CNN inference.

Findings

Reduced execution time for secure CNN inference.

Lower RAM usage through the splitting algorithm.

Enhanced MOTION2NX with tensorized primitives.

Abstract

This work contributes towards the development of an efficient and scalable open-source Secure Multi-Party Computation (SMPC) protocol on machines with moderate computational resources. We use the ABY2.0 SMPC protocol implemented on the C++ based MOTION2NX framework for secure convolutional neural network (CNN) inference application with semi-honest security. Our list of contributions are as follows. Firstly, we enhance MOTION2NX by providing a tensorized version of several primitive functions including the Hadamard product, indicator function and argmax function. Secondly, we adapt an existing Helper node algorithm, working in tandem with the ABY2.0 protocol, for efficient convolution computation to reduce execution time and RAM usage. Thirdly, we also present a novel splitting algorithm that divides the computations at each CNN layer into multiple configurable chunks. This novel splitting algorithm, providing significant reduction in RAM usage, is of independent interest and is applicable to general SMPC protocols.