HyPHEN: A Hybrid Packing Method and Optimizations for Homomorphic Encryption-Based Neural Networks

02/05/2023
by   Donghwan Kim, et al.
0

Convolutional neural network (CNN) inference using fully homomorphic encryption (FHE) is a promising private inference (PI) solution due to the capability of FHE that enables offloading the whole computation process to the server while protecting the privacy of sensitive user data. However, prior FHEbased CNN (HCNN) implementations are far from being practical due to the high computational and memory overheads of FHE. To overcome this limitation, we present HyPHEN, a deep HCNN construction that features an efficient FHE convolution algorithm, data packing methods (hybrid packing and image slicing), and FHE-specific optimizations. Such enhancements enable HyPHEN to substantially reduce the memory footprint and the number of expensive homomorphic operations, such as ciphertext rotation and bootstrapping. As a result, HyPHEN brings the latency of HCNN CIFAR-10 inference down to a practical level at 1.40s (ResNet20) and demonstrates HCNN ImageNet inference for the first time at 16.87s (ResNet18).

READ FULL TEXT

page 5

page 6

page 14

research
02/06/2021

FFConv: Fast Factorized Neural Network Inference on Encrypted Data

Homomorphic Encryption (HE), allowing computations on encrypted data (ci...
research
02/03/2023

TT-TFHE: a Torus Fully Homomorphic Encryption-Friendly Neural Network Architecture

This paper presents TT-TFHE, a deep neural network Fully Homomorphic Enc...
research
11/03/2020

Tile Tensors: A versatile data structure with descriptive shapes for homomorphic encryption

Moving from the theoretical promise of Fully Homomorphic Encryption (FHE...
research
01/29/2019

CaRENets: Compact and Resource-Efficient CNN for Homomorphic Inference on Encrypted Medical Images

Convolutional neural networks (CNNs) have enabled significant performanc...
research
10/15/2021

Efficient Representations for Privacy-Preserving Inference

Deep neural networks have a wide range of applications across multiple d...
research
08/25/2023

Falcon: Accelerating Homomorphically Encrypted Convolutions for Efficient Private Mobile Network Inference

Efficient networks, e.g., MobileNetV2, EfficientNet, etc, achieves state...
research
11/07/2018

Packing Sparse Convolutional Neural Networks for Efficient Systolic Array Implementations: Column Combining Under Joint Optimization

This paper describes a novel approach of packing sparse convolutional ne...

Please sign up or login with your details

Forgot password? Click here to reset