Split HE: Fast Secure Inference Combining Split Learning and Homomorphic Encryption

TL;DR

This paper introduces a fast, secure neural network inference protocol that combines split learning with homomorphic encryption, significantly improving speed and security for computer vision tasks.

Contribution

It proposes a novel protocol that enhances inference speed and security by integrating split learning with homomorphic encryption, evaluated on benchmark datasets.

Findings

Achieved 2.5x-10x faster inference times

Reduced communication costs by 14x-290x

Enhanced security against inference and extraction attacks

Abstract

This work presents a novel protocol for fast secure inference of neural networks applied to computer vision applications. It focuses on improving the overall performance of the online execution by deploying a subset of the model weights in plaintext on the client's machine, in the fashion of SplitNNs. We evaluate our protocol on benchmark neural networks trained on the CIFAR-10 dataset using SEAL via TenSEAL and discuss runtime and security performances. Empirical security evaluation using Membership Inference and Model Extraction attacks showed that the protocol was more resilient under the same attacks than a similar approach also based on SplitNN. When compared to related work, we demonstrate improvements of 2.5x-10x for the inference time and 14x-290x in communication costs.