A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiency

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shao, Jiawei, Li, Zijian, Sun, Wenqiang, Zhou, Tailin, Sun, Yuchang, Liu, Lumin, Lin, Zehong, Mao, Yuyi, Zhang, Jun
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913236027179008
author Shao, Jiawei
Li, Zijian
Sun, Wenqiang
Zhou, Tailin
Sun, Yuchang
Liu, Lumin
Lin, Zehong
Mao, Yuyi
Zhang, Jun
author_facet Shao, Jiawei
Li, Zijian
Sun, Wenqiang
Zhou, Tailin
Sun, Yuchang
Liu, Lumin
Lin, Zehong
Mao, Yuyi
Zhang, Jun
contents Federated learning (FL) has emerged as a secure paradigm for collaborative training among clients. Without data centralization, FL allows clients to share local information in a privacy-preserving manner. This approach has gained considerable attention, promoting numerous surveys to summarize the related works. However, the majority of these surveys concentrate on FL methods that share model parameters during the training process, while overlooking the possibility of sharing local information in other forms. In this paper, we present a systematic survey from a new perspective of what to share in FL, with an emphasis on the model utility, privacy leakage, and communication efficiency. First, we present a new taxonomy of FL methods in terms of three sharing methods, which respectively share model, synthetic data, and knowledge. Second, we analyze the vulnerability of different sharing methods to privacy attacks and review the defense mechanisms. Third, we conduct extensive experiments to compare the learning performance and communication overhead of various sharing methods in FL. Besides, we assess the potential privacy leakage through model inversion and membership inference attacks, while comparing the effectiveness of various defense approaches. Finally, we identify future research directions and conclude the survey.
format Preprint
id arxiv_https___arxiv_org_abs_2307_10655
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiency
Shao, Jiawei
Li, Zijian
Sun, Wenqiang
Zhou, Tailin
Sun, Yuchang
Liu, Lumin
Lin, Zehong
Mao, Yuyi
Zhang, Jun
Machine Learning
Cryptography and Security
Federated learning (FL) has emerged as a secure paradigm for collaborative training among clients. Without data centralization, FL allows clients to share local information in a privacy-preserving manner. This approach has gained considerable attention, promoting numerous surveys to summarize the related works. However, the majority of these surveys concentrate on FL methods that share model parameters during the training process, while overlooking the possibility of sharing local information in other forms. In this paper, we present a systematic survey from a new perspective of what to share in FL, with an emphasis on the model utility, privacy leakage, and communication efficiency. First, we present a new taxonomy of FL methods in terms of three sharing methods, which respectively share model, synthetic data, and knowledge. Second, we analyze the vulnerability of different sharing methods to privacy attacks and review the defense mechanisms. Third, we conduct extensive experiments to compare the learning performance and communication overhead of various sharing methods in FL. Besides, we assess the potential privacy leakage through model inversion and membership inference attacks, while comparing the effectiveness of various defense approaches. Finally, we identify future research directions and conclude the survey.
title A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiency
topic Machine Learning
Cryptography and Security
url https://arxiv.org/abs/2307.10655