FFConv: Fast Factorized Neural Network Inference on Encrypted Data

02/06/2021
by   Yuxiao Lu, et al.
8

Homomorphic Encryption (HE), allowing computations on encrypted data (ciphertext) without decrypting it first, enables secure but prohibitively slow Neural Network (HENN) inference for privacy-preserving applications in clouds. To reduce HENN inference latency, one approach is to pack multiple messages into a single ciphertext in order to reduce the number of ciphertexts and support massive parallelism of Homomorphic Multiply-Add (HMA) operations between ciphertexts. However, different ciphertext packing schemes have to be designed for different convolution layers and each of them introduces overheads that are far more expensive than HMA operations. In this paper, we propose a low-rank factorization method called FFConv to unify convolution and ciphertext packing. To our knowledge, FFConv is the first work that is capable of accelerating the overheads induced by different ciphertext packing schemes simultaneously, without incurring a significant increase in noise budget. Compared to prior art LoLa and Falcon, our method reduces the inference latency by up to 87 CIFAR-10.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/05/2023

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

Convolutional neural network (CNN) inference using fully homomorphic enc...
research
07/07/2022

HE-PEx: Efficient Machine Learning under Homomorphic Encryption using Pruning, Permutation and Expansion

Privacy-preserving neural network (NN) inference solutions have recently...
research
05/31/2021

HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture

Recently Homomorphic Encryption (HE) is used to implement Privacy-Preser...
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
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
04/19/2021

Vectorized Secure Evaluation of Decision Forests

As the demand for machine learning-based inference increases in tandem w...
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...

Please sign up or login with your details

Forgot password? Click here to reset