CryptoGRU: Low Latency Privacy-Preserving Text Analysis With GRU

10/22/2020
by   Bo Feng, et al.
18

Billions of text analysis requests containing private emails, personal text messages, and sensitive online reviews, are processed by recurrent neural networks (RNNs) deployed on public clouds every day. Although prior secure networks combine homomorphic encryption (HE) and garbled circuit (GC) to preserve users' privacy, naively adopting the HE and GC hybrid technique to implement RNNs suffers from long inference latency due to slow activation functions. In this paper, we present a HE and GC hybrid gated recurrent unit (GRU) network, CryptoGRU, for low-latency secure inferences. CryptoGRU replaces computationally expensive GC-based tanh with fast GC-based ReLU, and then quantizes sigmoid and ReLU with a smaller bit length to accelerate activations in a GRU. We evaluate CryptoGRU with multiple GRU models trained on 4 public datasets. Experimental results show CryptoGRU achieves top-notch accuracy and improves the secure inference latency by up to 138× over one of state-of-the-art secure networks on the Penn Treebank dataset.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/01/2019

SHE: A Fast and Accurate Privacy-Preserving Deep Neural Network Via Leveled TFHE and Logarithmic Data Representation

Homomorphic Encryption (HE) is one of the most promising security soluti...
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
01/18/2022

AESPA: Accuracy Preserving Low-degree Polynomial Activation for Fast Private Inference

Hybrid private inference (PI) protocol, which synergistically utilizes b...
research
05/23/2016

Path-Normalized Optimization of Recurrent Neural Networks with ReLU Activations

We investigate the parameter-space geometry of recurrent neural networks...
research
06/07/2020

AutoPrivacy: Automated Layer-wise Parameter Selection for Secure Neural Network Inference

Hybrid Privacy-Preserving Neural Network (HPPNN) implementing linear lay...
research
12/27/2018

Low Latency Privacy Preserving Inference

When applying machine learning to sensitive data, one has to balance bet...
research
02/04/2022

Selective Network Linearization for Efficient Private Inference

Private inference (PI) enables inference directly on cryptographically s...

Please sign up or login with your details

Forgot password? Click here to reset