Strategic Incentivization for Locally Differentially Private Federated Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pagoti, Yashwant Krishna, Sinha, Arunesh, Sural, Shamik
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911100584329216
author Pagoti, Yashwant Krishna
Sinha, Arunesh
Sural, Shamik
author_facet Pagoti, Yashwant Krishna
Sinha, Arunesh
Sural, Shamik
contents In Federated Learning (FL), multiple clients jointly train a machine learning model by sharing gradient information, instead of raw data, with a server over multiple rounds. To address the possibility of information leakage in spite of sharing only the gradients, Local Differential Privacy (LDP) is often used. In LDP, clients add a selective amount of noise to the gradients before sending the same to the server. Although such noise addition protects the privacy of clients, it leads to a degradation in global model accuracy. In this paper, we model this privacy-accuracy trade-off as a game, where the sever incentivizes the clients to add a lower degree of noise for achieving higher accuracy, while the clients attempt to preserve their privacy at the cost of a potential loss in accuracy. A token based incentivization mechanism is introduced in which the quantum of tokens credited to a client in an FL round is a function of the degree of perturbation of its gradients. The client can later access a newly updated global model only after acquiring enough tokens, which are to be deducted from its balance. We identify the players, their actions and payoff, and perform a strategic analysis of the game. Extensive experiments were carried out to study the impact of different parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2508_07138
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Strategic Incentivization for Locally Differentially Private Federated Learning
Pagoti, Yashwant Krishna
Sinha, Arunesh
Sural, Shamik
Machine Learning
Computer Science and Game Theory
In Federated Learning (FL), multiple clients jointly train a machine learning model by sharing gradient information, instead of raw data, with a server over multiple rounds. To address the possibility of information leakage in spite of sharing only the gradients, Local Differential Privacy (LDP) is often used. In LDP, clients add a selective amount of noise to the gradients before sending the same to the server. Although such noise addition protects the privacy of clients, it leads to a degradation in global model accuracy. In this paper, we model this privacy-accuracy trade-off as a game, where the sever incentivizes the clients to add a lower degree of noise for achieving higher accuracy, while the clients attempt to preserve their privacy at the cost of a potential loss in accuracy. A token based incentivization mechanism is introduced in which the quantum of tokens credited to a client in an FL round is a function of the degree of perturbation of its gradients. The client can later access a newly updated global model only after acquiring enough tokens, which are to be deducted from its balance. We identify the players, their actions and payoff, and perform a strategic analysis of the game. Extensive experiments were carried out to study the impact of different parameters.
title Strategic Incentivization for Locally Differentially Private Federated Learning
topic Machine Learning
Computer Science and Game Theory
url https://arxiv.org/abs/2508.07138