ULDP-FL: Federated Learning with Across Silo User-Level Differential Privacy

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kato, Fumiyuki, Xiong, Li, Takagi, Shun, Cao, Yang, Yoshikawa, Masatoshi
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911918763016192
author Kato, Fumiyuki
Xiong, Li
Takagi, Shun
Cao, Yang
Yoshikawa, Masatoshi
author_facet Kato, Fumiyuki
Xiong, Li
Takagi, Shun
Cao, Yang
Yoshikawa, Masatoshi
contents Differentially Private Federated Learning (DP-FL) has garnered attention as a collaborative machine learning approach that ensures formal privacy. Most DP-FL approaches ensure DP at the record-level within each silo for cross-silo FL. However, a single user's data may extend across multiple silos, and the desired user-level DP guarantee for such a setting remains unknown. In this study, we present Uldp-FL, a novel FL framework designed to guarantee user-level DP in cross-silo FL where a single user's data may belong to multiple silos. Our proposed algorithm directly ensures user-level DP through per-user weighted clipping, departing from group-privacy approaches. We provide a theoretical analysis of the algorithm's privacy and utility. Additionally, we enhance the utility of the proposed algorithm with an enhanced weighting strategy based on user record distribution and design a novel private protocol that ensures no additional information is revealed to the silos and the server. Experiments on real-world datasets show substantial improvements in our methods in privacy-utility trade-offs under user-level DP compared to baseline methods. To the best of our knowledge, our work is the first FL framework that effectively provides user-level DP in the general cross-silo FL setting.
format Preprint
id arxiv_https___arxiv_org_abs_2308_12210
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle ULDP-FL: Federated Learning with Across Silo User-Level Differential Privacy
Kato, Fumiyuki
Xiong, Li
Takagi, Shun
Cao, Yang
Yoshikawa, Masatoshi
Machine Learning
Cryptography and Security
Differentially Private Federated Learning (DP-FL) has garnered attention as a collaborative machine learning approach that ensures formal privacy. Most DP-FL approaches ensure DP at the record-level within each silo for cross-silo FL. However, a single user's data may extend across multiple silos, and the desired user-level DP guarantee for such a setting remains unknown. In this study, we present Uldp-FL, a novel FL framework designed to guarantee user-level DP in cross-silo FL where a single user's data may belong to multiple silos. Our proposed algorithm directly ensures user-level DP through per-user weighted clipping, departing from group-privacy approaches. We provide a theoretical analysis of the algorithm's privacy and utility. Additionally, we enhance the utility of the proposed algorithm with an enhanced weighting strategy based on user record distribution and design a novel private protocol that ensures no additional information is revealed to the silos and the server. Experiments on real-world datasets show substantial improvements in our methods in privacy-utility trade-offs under user-level DP compared to baseline methods. To the best of our knowledge, our work is the first FL framework that effectively provides user-level DP in the general cross-silo FL setting.
title ULDP-FL: Federated Learning with Across Silo User-Level Differential Privacy
topic Machine Learning
Cryptography and Security
url https://arxiv.org/abs/2308.12210