Differential privacy in deep learning: Privacy and beyond

Y Wang, Q Wang, L Zhao, C Wang - Future Generation Computer Systems, 2023 - Elsevier
Motivated by the security risks of deep neural networks, such as various membership and
attribute inference attacks, differential privacy has emerged as a promising approach for …

Bypassing the ambient dimension: Private sgd with gradient subspace identification

Y Zhou, ZS Wu, A Banerjee - arXiv preprint arXiv:2007.03813, 2020 - arxiv.org
Differentially private SGD (DP-SGD) is one of the most popular methods for solving
differentially private empirical risk minimization (ERM). Due to its noisy perturbation on each …

Survey: Leakage and privacy at inference time

M Jegorova, C Kaul, C Mayor, AQ O'Neil… - … on Pattern Analysis …, 2022 - ieeexplore.ieee.org
Leakage of data from publicly available Machine Learning (ML) models is an area of
growing significance since commercial and government applications of ML can draw on …

Differentially private empirical risk minimization with non-convex loss functions

D Wang, C Chen, J Xu - International Conference on …, 2019 - proceedings.mlr.press
We study the problem of Empirical Risk Minimization (ERM) with (smooth) non-convex loss
functions under the differential-privacy (DP) model. Existing approaches for this problem …

Faster rates of convergence to stationary points in differentially private optimization

R Arora, R Bassily, T González… - International …, 2023 - proceedings.mlr.press
We study the problem of approximating stationary points of Lipschitz and smooth functions
under $(\varepsilon,\delta) $-differential privacy (DP) in both the finite-sum and stochastic …

Differentially private federated learning via reconfigurable intelligent surface

Y Yang, Y Zhou, Y Wu, Y Shi - IEEE Internet of Things journal, 2022 - ieeexplore.ieee.org
Federated learning (FL), as a disruptive machine learning (ML) paradigm, enables the
collaborative training of a global model over decentralized local data sets without sharing …

Adaptive privacy preserving deep learning algorithms for medical data

X Zhang, J Ding, M Wu, STC Wong… - Proceedings of the …, 2021 - openaccess.thecvf.com
Deep learning holds a great promise of revolutionizing healthcare and medicine.
Unfortunately, various inference attack models demonstrated that deep learning puts …

On sparse linear regression in the local differential privacy model

D Wang, J Xu - International Conference on Machine …, 2019 - proceedings.mlr.press
In this paper, we study the sparse linear regression problem under the Local Differential
Privacy (LDP) model. We first show that polynomial dependency on the dimensionality $ p …

Differentially private non-convex learning for multi-layer neural networks

H Shen, CL Wang, Z Xiang, Y Ying, D Wang - arXiv preprint arXiv …, 2023 - arxiv.org
This paper focuses on the problem of Differentially Private Stochastic Optimization for (multi-
layer) fully connected neural networks with a single output node. In the first part, we examine …

Pairwise learning with differential privacy guarantees

M Huai, D Wang, C Miao, J Xu, A Zhang - Proceedings of the AAAI …, 2020 - aaai.org
Pairwise learning has received much attention recently as it is more capable of modeling the
relative relationship between pairs of samples. Many machine learning tasks can be …