Differentially-Private Multi-Tier Federated Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Evan, Lin, Frank Po-Chen, Han, Dong-Jun, Brinton, Christopher G.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917830791790592
author Chen, Evan
Lin, Frank Po-Chen
Han, Dong-Jun
Brinton, Christopher G.
author_facet Chen, Evan
Lin, Frank Po-Chen
Han, Dong-Jun
Brinton, Christopher G.
contents While federated learning (FL) eliminates the transmission of raw data over a network, it is still vulnerable to privacy breaches from the communicated model parameters. In this work, we propose Multi-Tier Federated Learning with Multi-Tier Differential Privacy (M^2FDP), a DP-enhanced FL methodology for jointly optimizing privacy and performance in hierarchical networks. One of the key concepts of M^2FDP is to extend the concept of HDP towards Multi-Tier Differential Privacy (MDP), while also adapting DP noise injection at different layers of an established FL hierarchy -- edge devices, edge servers, and cloud servers -- according to the trust models within particular subnetworks. We conduct a comprehensive analysis of the convergence behavior of M^2FDP, revealing conditions on parameter tuning under which the training process converges sublinearly to a finite stationarity gap that depends on the network hierarchy, trust model, and target privacy level. Subsequent numerical evaluations demonstrate that M^2FDP obtains substantial improvements in these metrics over baselines for different privacy budgets, and validate the impact of different system configurations.
format Preprint
id arxiv_https___arxiv_org_abs_2401_11592
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Differentially-Private Multi-Tier Federated Learning
Chen, Evan
Lin, Frank Po-Chen
Han, Dong-Jun
Brinton, Christopher G.
Machine Learning
Cryptography and Security
Distributed, Parallel, and Cluster Computing
While federated learning (FL) eliminates the transmission of raw data over a network, it is still vulnerable to privacy breaches from the communicated model parameters. In this work, we propose Multi-Tier Federated Learning with Multi-Tier Differential Privacy (M^2FDP), a DP-enhanced FL methodology for jointly optimizing privacy and performance in hierarchical networks. One of the key concepts of M^2FDP is to extend the concept of HDP towards Multi-Tier Differential Privacy (MDP), while also adapting DP noise injection at different layers of an established FL hierarchy -- edge devices, edge servers, and cloud servers -- according to the trust models within particular subnetworks. We conduct a comprehensive analysis of the convergence behavior of M^2FDP, revealing conditions on parameter tuning under which the training process converges sublinearly to a finite stationarity gap that depends on the network hierarchy, trust model, and target privacy level. Subsequent numerical evaluations demonstrate that M^2FDP obtains substantial improvements in these metrics over baselines for different privacy budgets, and validate the impact of different system configurations.
title Differentially-Private Multi-Tier Federated Learning
topic Machine Learning
Cryptography and Security
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2401.11592