Accuracy-Privacy Trade-off in the Mitigation of Membership Inference Attack in Federated Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ahamed, Sayyed Farid, Banerjee, Soumya, Roy, Sandip, Quinn, Devin, Vucovich, Marc, Choi, Kevin, Rahman, Abdul, Hu, Alison, Bowen, Edward, Shetty, Sachin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914889842294784
author Ahamed, Sayyed Farid
Banerjee, Soumya
Roy, Sandip
Quinn, Devin
Vucovich, Marc
Choi, Kevin
Rahman, Abdul
Hu, Alison
Bowen, Edward
Shetty, Sachin
author_facet Ahamed, Sayyed Farid
Banerjee, Soumya
Roy, Sandip
Quinn, Devin
Vucovich, Marc
Choi, Kevin
Rahman, Abdul
Hu, Alison
Bowen, Edward
Shetty, Sachin
contents Over the last few years, federated learning (FL) has emerged as a prominent method in machine learning, emphasizing privacy preservation by allowing multiple clients to collaboratively build a model while keeping their training data private. Despite this focus on privacy, FL models are susceptible to various attacks, including membership inference attacks (MIAs), posing a serious threat to data confidentiality. In a recent study, Rezaei \textit{et al.} revealed the existence of an accuracy-privacy trade-off in deep ensembles and proposed a few fusion strategies to overcome it. In this paper, we aim to explore the relationship between deep ensembles and FL. Specifically, we investigate whether confidence-based metrics derived from deep ensembles apply to FL and whether there is a trade-off between accuracy and privacy in FL with respect to MIA. Empirical investigations illustrate a lack of a non-monotonic correlation between the number of clients and the accuracy-privacy trade-off. By experimenting with different numbers of federated clients, datasets, and confidence-metric-based fusion strategies, we identify and analytically justify the clear existence of the accuracy-privacy trade-off.
format Preprint
id arxiv_https___arxiv_org_abs_2407_19119
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Accuracy-Privacy Trade-off in the Mitigation of Membership Inference Attack in Federated Learning
Ahamed, Sayyed Farid
Banerjee, Soumya
Roy, Sandip
Quinn, Devin
Vucovich, Marc
Choi, Kevin
Rahman, Abdul
Hu, Alison
Bowen, Edward
Shetty, Sachin
Machine Learning
Artificial Intelligence
Cryptography and Security
Over the last few years, federated learning (FL) has emerged as a prominent method in machine learning, emphasizing privacy preservation by allowing multiple clients to collaboratively build a model while keeping their training data private. Despite this focus on privacy, FL models are susceptible to various attacks, including membership inference attacks (MIAs), posing a serious threat to data confidentiality. In a recent study, Rezaei \textit{et al.} revealed the existence of an accuracy-privacy trade-off in deep ensembles and proposed a few fusion strategies to overcome it. In this paper, we aim to explore the relationship between deep ensembles and FL. Specifically, we investigate whether confidence-based metrics derived from deep ensembles apply to FL and whether there is a trade-off between accuracy and privacy in FL with respect to MIA. Empirical investigations illustrate a lack of a non-monotonic correlation between the number of clients and the accuracy-privacy trade-off. By experimenting with different numbers of federated clients, datasets, and confidence-metric-based fusion strategies, we identify and analytically justify the clear existence of the accuracy-privacy trade-off.
title Accuracy-Privacy Trade-off in the Mitigation of Membership Inference Attack in Federated Learning
topic Machine Learning
Artificial Intelligence
Cryptography and Security
url https://arxiv.org/abs/2407.19119