BAYHENN: Combining Bayesian Deep Learning and Homomorphic Encryption for Secure DNN Inference

06/03/2019
by   Peichen Xie, et al.
0

Recently, deep learning as a service (DLaaS) has emerged as a promising way to facilitate the employment of deep neural networks (DNNs) for various purposes. However, using DLaaS also causes potential privacy leakage from both clients and cloud servers. This privacy issue has fueled the research interests on the privacy-preserving inference of DNN models in the cloud service. In this paper, we present a practical solution named BAYHENN for secure DNN inference. It can protect both the client's privacy and server's privacy at the same time. The key strategy of our solution is to combine homomorphic encryption and Bayesian neural networks. Specifically, we use homomorphic encryption to protect a client's raw data and use Bayesian neural networks to protect the DNN weights in a cloud server. To verify the effectiveness of our solution, we conduct experiments on MNIST and a real-life clinical dataset. Our solution achieves consistent latency decreases on both tasks. In particular, our method can outperform the best existing method (GAZELLE) by about 5x, in terms of end-to-end latency.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/07/2021

Privacy-preserving Cloud-based DNN Inference

Deep learning as a service (DLaaS) has been intensively studied to facil...
research
07/01/2021

VeriDL: Integrity Verification of Outsourced Deep Learning Services (Extended Version)

Deep neural networks (DNNs) are prominent due to their superior performa...
research
10/01/2018

Privado: Practical and Secure DNN Inference

Recently, cloud providers have extended support for trusted hardware pri...
research
03/26/2020

Corella: A Private Multi Server Learning Approach based on Correlated Queries

The emerging applications of machine learning algorithms on mobile devic...
research
05/31/2020

Cheetah: Optimizations and Methods for PrivacyPreserving Inference via Homomorphic Encryption

As the application of deep learning continues to grow, so does the amoun...
research
05/26/2019

Shredder: Learning Noise to Protect Privacy with Partial DNN Inference on the Edge

A wide variety of DNN applications increasingly rely on the cloud to per...
research
11/04/2021

CryptoNite: Revealing the Pitfalls of End-to-End Private Inference at Scale

The privacy concerns of providing deep learning inference as a service h...

Please sign up or login with your details

Forgot password? Click here to reset