Heterogeneous Gaussian mechanism: Preserving differential privacy in deep learning with provable robustness

Nhat Hai Phan, Minh N. Vu, Yang Liu, Ruoming Jin, Dejing Dou, Xintao Wu, My T. Thai

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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, infty), 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.

Original languageEnglish (US)
Title of host publicationProceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
EditorsSarit Kraus
PublisherInternational Joint Conferences on Artificial Intelligence
Pages4753-4759
Number of pages7
ISBN (Electronic)9780999241141
StatePublished - Jan 1 2019
Event28th International Joint Conference on Artificial Intelligence, IJCAI 2019 - Macao, China
Duration: Aug 10 2019Aug 16 2019

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
Volume2019-August

Conference

Conference28th International Joint Conference on Artificial Intelligence, IJCAI 2019
CountryChina
CityMacao
Period8/10/198/16/19

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Phan, N. H., Vu, M. N., Liu, Y., Jin, R., Dou, D., Wu, X., & Thai, M. T. (2019). Heterogeneous Gaussian mechanism: Preserving differential privacy in deep learning with provable robustness. In S. Kraus (Ed.), Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019 (pp. 4753-4759). (IJCAI International Joint Conference on Artificial Intelligence; Vol. 2019-August). International Joint Conferences on Artificial Intelligence.