Differentially Private Federated Learning

Differentially private federated learning (DPFL) aims to enable collaborative model training across multiple devices without compromising individual data privacy, using differential privacy mechanisms to add noise and protect sensitive information. Current research focuses on improving the accuracy of DPFL models by addressing the trade-off between privacy and utility through techniques like personalized optimization, robust clustering of clients based on model updates and loss, and noise-aware aggregation strategies. These advancements are crucial for deploying privacy-preserving machine learning in real-world applications, particularly in sensitive domains like healthcare and finance, where data sharing is restricted.

Papers

October 21, 2024

DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning using Packed Secret Sharing
Alexander Bienstock, Ujjwal Kumar, Antigoni Polychroniadou
LeArning Abstract Differential Privacy Privacy Utility Secret Sharing Unfolded D ADMM Cryptographic Protocol Differentially Private Federated Learning

September 20, 2024

DP$^2$-FedSAM: Enhancing Differentially Private Federated Learning Through Personalized Sharpness-Aware Minimization
Zhenxiao Zhang, Yuanxiong Guo, Yanmin Gong
Personalized Federated Learning Sharpness Aware Minimization Private Federated Learning Differentially Private Federated Learning

June 5, 2024

Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learning
Saber Malekmohammadi, Yaoliang Yu, Yang Cao
Differential Privacy Robust Version Privacy Analysis Privacy Parameter Differentially Private Federated Learning Noise Based

May 29, 2024

Mitigating Disparate Impact of Differential Privacy in Federated Learning through Robust Clustering
Saber Malekmohammadi, Afaf Taik, Golnoosh Farnadi
Differential Privacy Decentralized Machine Learning Privacy Sensitive Robust Clustering Disparate Impact Differentially Private Federated Learning

May 9, 2024

Age Aware Scheduling for Differentially-Private Federated Learning
Kuan-Yu Lin, Hsuan-Yin Lin, Yu-Pin Hsu, Yu-Chih Huang
Differential Privacy Time Series Three Way Differentially Private Federated Learning

December 27, 2023

A Theoretical Analysis of Efficiency Constrained Utility-Privacy Bi-Objective Optimization in Federated Learning
Hanlin Gu, Xinyuan Zhao, Gongxi Zhu, Yuxing Han, Yan Kang, Lixin Fan, Qiang Yang
High Efficiency Differential Privacy Theoretical Analysis Utility Privacy Trade Differentially Private Federated Learning

May 1, 2023

Towards the Flatter Landscape and Better Generalization in Federated Learning under Client-level Differential Privacy
Yifan Shi, Kang Wei, Li Shen, Yingqi Liu, Xueqian Wang, Bo Yuan, Dacheng Tao
Better Generalization Differentially Private Differentially Private Federated Learning Perturbation Robustness Client Level Differential Privacy Return Landscape

March 20, 2023

Make Landscape Flatter in Differentially Private Federated Learning
Yifan Shi, Yingqi Liu, Kang Wei, Li Shen, Xueqian Wang, Dacheng Tao
Private Federated Learning Differentially Private Differentially Private Federated Learning Return Landscape

July 24, 2022

Mitigating the Performance Sacrifice in DP-Satisfied Federated Settings through Graph Contrastive Learning
Haoran Yang, Xiangyu Zhao, Muyang Li, Hongxu Chen, Guandong Xu
Differential Privacy Graph Learning Trade Offs Graph Learning Model Differentially Private Federated Learning Proximity Graph

February 15, 2022

Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacy
Rui Hu, Yanmin Gong, Yuanxiong Guo
Differential Privacy Privacy Analysis Sparse Perturbation Differentially Private Federated Learning Client Level Differential Privacy

Differentially Private Federated Learning

Papers

DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning using Packed Secret Sharing

DP$^2$-FedSAM: Enhancing Differentially Private Federated Learning Through Personalized Sharpness-Aware Minimization

Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learning

Mitigating Disparate Impact of Differential Privacy in Federated Learning through Robust Clustering

Age Aware Scheduling for Differentially-Private Federated Learning

A Theoretical Analysis of Efficiency Constrained Utility-Privacy Bi-Objective Optimization in Federated Learning

Towards the Flatter Landscape and Better Generalization in Federated Learning under Client-level Differential Privacy

Make Landscape Flatter in Differentially Private Federated Learning

Mitigating the Performance Sacrifice in DP-Satisfied Federated Settings through Graph Contrastive Learning

Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacy