Heterogeneous Gaussian Mechanism: Preserving Differential Privacy in Deep Learning with Provable Robustness

06/02/2019
by   NhatHai Phan, et al.
0

In this paper, we propose a novel Heterogeneous Gaussian Mechanism (HGM) to preserve differential privacy in deep neural networks, with provable robustness against adversarial examples. We first relax the constraint of the privacy budget in the traditional Gaussian Mechanism from (0, 1] to (0, ∞), with a new bound of the noise scale to preserve differential privacy. The noise in our mechanism can be arbitrarily redistributed, offering a distinctive ability to address the trade-off between model utility and privacy loss. To derive provable robustness, our HGM is applied to inject Gaussian noise into the first hidden layer. Then, a tighter robustness bound is proposed. Theoretical analysis and thorough evaluations show that our mechanism notably improves the robustness of differentially private deep neural networks, compared with baseline approaches, under a variety of model attacks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/23/2019

Preserving Differential Privacy in Adversarial Learning with Provable Robustness

In this paper, we aim to develop a novel mechanism to preserve different...
research
09/18/2017

Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learning

In this paper, we focus on developing a novel mechanism to preserve diff...
research
06/07/2021

Photonic Differential Privacy with Direct Feedback Alignment

Optical Processing Units (OPUs) – low-power photonic chips dedicated to ...
research
04/15/2019

Differential Privacy for Eye-Tracking Data

As large eye-tracking datasets are created, data privacy is a pressing c...
research
01/14/2020

Differentially Private and Fair Classification via Calibrated Functional Mechanism

Machine learning is increasingly becoming a powerful tool to make decisi...
research
08/28/2019

Rényi Differential Privacy of the Sampled Gaussian Mechanism

The Sampled Gaussian Mechanism (SGM)---a composition of subsampling and ...
research
06/25/2017

Preserving Differential Privacy in Convolutional Deep Belief Networks

The remarkable development of deep learning in medicine and healthcare d...

Please sign up or login with your details

Forgot password? Click here to reset