Differential Privacy

Differential privacy (DP) is a rigorous framework for ensuring data privacy in machine learning by adding carefully calibrated noise to model training processes. Current research focuses on improving the accuracy of DP models, particularly for large-scale training, through techniques like adaptive noise allocation, Kalman filtering for noise reduction, and novel gradient processing methods. This active area of research is crucial for enabling the responsible use of sensitive data in various applications, ranging from healthcare and finance to natural language processing and smart grids, while maintaining strong privacy guarantees.

754papers

Papers - Page 31

February 11, 2023

February 9, 2023

On the Privacy-Robustness-Utility Trilemma in Distributed Learning
Utility Privacy Trade Native Robustness Robust Aggregation Rule Distributed Learning Adversarial Learning Differential Privacy

February 8, 2023

February 6, 2023

February 3, 2023

Private, fair and accurate: Training large-scale, privacy-preserving AI models in medical imaging
Fairness Estimation Privacy Preserving Training Large Scale Training Privacy Preserving Differential Privacy Medical Imaging

February 2, 2023

February 1, 2023

Analyzing Leakage of Personally Identifiable Information in Language Models
Personal Information Language Model Differential Privacy Defense Algorithm Leakage Attack Life Event

January 31, 2023

General Gaussian Noise Mechanisms and Their Optimality for Unbiased Mean Estimation
Gaussian Mechanism Near Optimality High Dimensional Private Mean Estimation Local Differential Privacy Unbiased Estimator Differential Privacy

January 30, 2023

Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser Models
Equivariant Convolutional Neural Network Private Stochastic Gradient Descent Equivariant Map Differential Privacy Sparse Local Model

January 29, 2023

Concurrent Shuffle Differential Privacy Under Continual Observation
Shuffle Model Differential Privacy

January 28, 2023

January 27, 2023

FedPH: Privacy-enhanced Heterogeneous Federated Learning
Privacy Preserving Heterogeneous Federated Learning Differential Privacy Federated Learning

January 24, 2023

Membership Inference of Diffusion Models
Membership Inference Attack Membership Inference Diffusion Model Differential Privacy Privacy Sensitive Likelihood Ratio Attack

January 22, 2023

Differentially Private Natural Language Models: Recent Advances and Future Directions
Natural Language Processing Language Model Future Direction Differential Privacy Private Data Analysis Recent Advance

January 21, 2023

Statistical Theory of Differentially Private Marginal-based Data Synthesis Algorithms
Marginal Distribution Statistical Model Differential Privacy Probabilistic Graphical Model

Differential Privacy

Papers - Page 31

Differentially Private Normalizing Flows for Density Estimation, Data Synthesis, and Variational Inference with Application to Electronic Health Records

On Differential Privacy and Adaptive Data Analysis with Bounded Space

On the Privacy-Robustness-Utility Trilemma in Distributed Learning

Exploratory Analysis of Federated Learning Methods with Differential Privacy on MIMIC-III

DIFF2: Differential Private Optimization via Gradient Differences for Nonconvex Distributed Learning

An Empirical Analysis of Fairness Notions under Differential Privacy

On Private and Robust Bandits

Private, fair and accurate: Training large-scale, privacy-preserving AI models in medical imaging

Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacy

FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations

Analyzing Leakage of Personally Identifiable Information in Language Models

General Gaussian Noise Mechanisms and Their Optimality for Unbiased Mean Estimation

Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser Models

Concurrent Shuffle Differential Privacy Under Continual Observation

Context-Aware Differential Privacy for Language Modeling

(Private) Kernelized Bandits with Distributed Biased Feedback

FedPH: Privacy-enhanced Heterogeneous Federated Learning

Membership Inference of Diffusion Models

Differentially Private Natural Language Models: Recent Advances and Future Directions

Statistical Theory of Differentially Private Marginal-based Data Synthesis Algorithms