Differential privacy in deep learning: Privacy and beyond
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 …
attribute inference attacks, differential privacy has emerged as a promising approach for …
Bypassing the ambient dimension: Private sgd with gradient subspace identification
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 …
differentially private empirical risk minimization (ERM). Due to its noisy perturbation on each …
Survey: Leakage and privacy at inference time
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 …
growing significance since commercial and government applications of ML can draw on …
Differentially private empirical risk minimization with non-convex loss functions
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 …
functions under the differential-privacy (DP) model. Existing approaches for this problem …
Faster rates of convergence to stationary points in differentially private optimization
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 …
under $(\varepsilon,\delta) $-differential privacy (DP) in both the finite-sum and stochastic …
Differentially private federated learning via reconfigurable intelligent surface
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 …
collaborative training of a global model over decentralized local data sets without sharing …
Adaptive privacy preserving deep learning algorithms for medical data
Deep learning holds a great promise of revolutionizing healthcare and medicine.
Unfortunately, various inference attack models demonstrated that deep learning puts …
Unfortunately, various inference attack models demonstrated that deep learning puts …
On sparse linear regression in the local differential privacy model
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 …
Privacy (LDP) model. We first show that polynomial dependency on the dimensionality $ p …
Differentially private non-convex learning for multi-layer neural networks
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 …
layer) fully connected neural networks with a single output node. In the first part, we examine …
Pairwise learning with differential privacy guarantees
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 …
relative relationship between pairs of samples. Many machine learning tasks can be …