Private Federated Learning

Private federated learning aims to enable collaborative model training across multiple devices without compromising data privacy, primarily focusing on mitigating information leakage through model updates. Current research emphasizes techniques like differential privacy (DP), often combined with secure aggregation and various optimization methods (e.g., sharpness-aware minimization, cubic-regularized Newton methods) to enhance the privacy-utility trade-off, and explores efficient compression and quantization strategies to reduce communication overhead. This field is crucial for advancing trustworthy machine learning applications, particularly in sensitive domains like healthcare and finance, by providing rigorous privacy guarantees while maintaining model accuracy.

Papers

October 24, 2024

LanFL: Differentially Private Federated Learning with Large Language Models using Synthetic Samples
Huiyu Wu, Diego Klabjan
Large Language Model Full Model Synthetic Data Federated Learning Large Language Private Federated Learning Synthetic Sample

September 30, 2024

Comments on "Privacy-Enhanced Federated Learning Against Poisoning Adversaries"
Thomas Schneider, Ajith Suresh, Hossein Yalame
Federated Learning Poisoning Attack Homomorphic Encryption Private Federated Learning Online Comment Privacy Threat Privacy Framework

September 20, 2024

August 18, 2024

Mitigating Noise Detriment in Differentially Private Federated Learning with Model Pre-training
Huitong Jin, Yipeng Zhou, Laizhong Cui, Quan Z. Sheng
Pre Trained Model Private Federated Learning Pre Training Model Model Gradient Mitigating Noise

August 8, 2024

Federated Cubic Regularized Newton Learning with Sparsification-amplified Differential Privacy
Wei Huo, Changxin Liu, Kemi Ding, Karl Henrik Johansson, Ling Shi
Private Federated Learning Differential Privacy Guarantee Federated Learning Framework Newton Method

July 27, 2024

On Joint Noise Scaling in Differentially Private Federated Learning with Multiple Local Steps
Mikko A. Heikkilä
Differential Privacy Secure Aggregation Private Federated Learning Joint Denoising Training Data Privacy

July 12, 2024

Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses
Changyu Gao, Andrew Lowy, Xingyu Zhou, Stephen J. Wright
Differential Privacy Communication Efficient Convex Loss Private Federated Learning Cross Silo Federated Learning Risk Bound

May 29, 2024

LoByITFL: Low Communication Secure and Private Federated Learning
Yue Xia, Christoph Hofmeister, Maximilian Egger, Rawad Bitar
Federated Learning Private Federated Learning FL Algorithm Secure Communication

May 14, 2024

Differentially Private Federated Learning: A Systematic Review
Jie Fu, Yuan Hong, Xinpeng Ling, Leixia Wang, Xun Ran, Zhiyu Sun, Wendy Hui Wang, Zhili Chen, Yang Cao
Differential Privacy Systematic Review Private Federated Learning

May 10, 2024

DP-DyLoRA: Fine-Tuning Transformer-Based Models On-Device under Differentially Private Federated Learning using Dynamic Low-Rank Adaptation
Jie Xu, Karthikeyan Saravanan, Rogier van Dalen, Haaris Mehmood, David Tuckey, Mete Ozay
Differential Privacy Transformer Based Model Low Rank Adaptation Privacy Guarantee Private Federated Learning

May 6, 2024

Differentially Private Federated Learning without Noise Addition: When is it Possible?
Jiang Zhang, Konstantinos Psounis, Salman Avestimehr
Secure Aggregation Private Federated Learning Differential Privacy Guarantee

April 25, 2024

Differentially Private Federated Learning: Servers Trustworthiness, Estimation, and Statistical Inference
Zhe Zhang, Ryumei Nakada, Linjun Zhang
Differential Privacy High Dimensional Estimation Task Private Federated Learning Statistical Inference High Dimensional Problem Trustworthy Computing Simultaneous Inference

April 15, 2024

Federated Learning on Riemannian Manifolds with Differential Privacy
Zhenwei Huang, Wen Huang, Pratik Jawanpuria, Bamdev Mishra
Differential Privacy Private Federated Learning Riemannian Manifold Riemannian Geometry Convergence Property

April 9, 2024

pfl-research: simulation framework for accelerating research in Private Federated Learning
Filip Granqvist, Congzheng Song, Áine Cahill, Rogier van Dalen, Martin Pelikan, Yi Sheng Chan, Xiaojun Feng, Natarajan Krishnaswami, Vojta Jina, Mona Chitnis
DH Research Private Federated Learning Simulation Framework Tensorflow Probability Open Source Federated Learning Framework

March 26, 2024

Enhancing Privacy in Federated Learning through Local Training
Nicola Bastianello, Changxin Liu, Karl H. Johansson
Private Federated Learning Local Training Protecting Privacy Training Epoch

March 25, 2024

Differentially Private Online Federated Learning with Correlated Noise
Jiaojiao Zhang, Linglingzhi Zhu, Mikael Johansson
Private Algorithm Private Federated Learning Strong Convexity Correlated Noise

March 12, 2024

Efficient Language Model Architectures for Differentially Private Federated Learning
Jae Hun Ro, Srinadh Bhojanapalli, Zheng Xu, Yanxiang Zhang, Ananda Theertha Suresh
Neural Language Model Recurrent Network Private Federated Learning Scale Invariant SGD Style

March 10, 2024

Fluent: Round-efficient Secure Aggregation for Private Federated Learning
Xincheng Li, Jianting Ning, Geong Sen Poh, Leo Yu Zhang, Xinchun Yin, Tianwei Zhang
Secure Aggregation Private Federated Learning Secret Sharing

February 29, 2024

SPriFed-OMP: A Differentially Private Federated Learning Algorithm for Sparse Basis Recovery
Ajinkya Kiran Mulay, Xiaojun Lin
Private Federated Learning Differential Privacy SGD Sparse Reconstruction Orthogonal Matching Pursuit

Private Federated Learning

Papers

LanFL: Differentially Private Federated Learning with Large Language Models using Synthetic Samples

Comments on "Privacy-Enhanced Federated Learning Against Poisoning Adversaries"

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

CorBin-FL: A Differentially Private Federated Learning Mechanism using Common Randomness

Mitigating Noise Detriment in Differentially Private Federated Learning with Model Pre-training

Federated Cubic Regularized Newton Learning with Sparsification-amplified Differential Privacy

On Joint Noise Scaling in Differentially Private Federated Learning with Multiple Local Steps

Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses

LoByITFL: Low Communication Secure and Private Federated Learning

Differentially Private Federated Learning: A Systematic Review

DP-DyLoRA: Fine-Tuning Transformer-Based Models On-Device under Differentially Private Federated Learning using Dynamic Low-Rank Adaptation

Differentially Private Federated Learning without Noise Addition: When is it Possible?

Differentially Private Federated Learning: Servers Trustworthiness, Estimation, and Statistical Inference

Federated Learning on Riemannian Manifolds with Differential Privacy

pfl-research: simulation framework for accelerating research in Private Federated Learning

Enhancing Privacy in Federated Learning through Local Training

Differentially Private Online Federated Learning with Correlated Noise

Efficient Language Model Architectures for Differentially Private Federated Learning

Fluent: Round-efficient Secure Aggregation for Private Federated Learning

SPriFed-OMP: A Differentially Private Federated Learning Algorithm for Sparse Basis Recovery