Vulnerabilities of NSPFL: Privacy-Preserving Federated Learning With Data Integrity Auditing

Jiahui Wu; Fucai Luo; Tiecheng Sun; Weizhe Zhang

doi:10.1109/TIFS.2025.3551640

Vulnerabilities of NSPFL: Privacy-Preserving Federated Learning With Data Integrity Auditing

Jiahui Wu
, Fucai Luo
, Tiecheng Sun
, Weizhe Zhang^*

^*Corresponding author for this work

Department of New Networks
Zhejiang Gongshang University

Research output: Contribution to journal › Article › peer-review

4 Scopus citations

Abstract

The secure and privacy-preserving federated learning scheme, NSPFL, aims to safeguard data privacy while also auditing data integrity. The solution provided by this scheme is highly novel. However, NSPFL has significant design shortcomings in terms of both privacy protection and data integrity verification. This work identifies specific issues within NSPFL and proposes effective countermeasures. Furthermore, our proposed solution can serve as a general approach for privacy-preserving multiparty computations, safeguarding privacy while enhancing efficiency.

Original language	English
Pages (from-to)	3907-3908
Number of pages	2
Journal	IEEE Transactions on Information Forensics and Security
Volume	20
DOIs	https://doi.org/10.1109/TIFS.2025.3551640
State	Published - 2025
Externally published	Yes

Keywords

Privacy protection
data integrity auditing
federated learning (FL)
vulnerabilities

Access to Document

10.1109/TIFS.2025.3551640

Cite this

@article{6bdf0ce5dd6048afbce73d29ef5bf9d3,

title = "Vulnerabilities of NSPFL: Privacy-Preserving Federated Learning With Data Integrity Auditing",

abstract = "The secure and privacy-preserving federated learning scheme, NSPFL, aims to safeguard data privacy while also auditing data integrity. The solution provided by this scheme is highly novel. However, NSPFL has significant design shortcomings in terms of both privacy protection and data integrity verification. This work identifies specific issues within NSPFL and proposes effective countermeasures. Furthermore, our proposed solution can serve as a general approach for privacy-preserving multiparty computations, safeguarding privacy while enhancing efficiency.",

keywords = "Privacy protection, data integrity auditing, federated learning (FL), vulnerabilities",

author = "Jiahui Wu and Fucai Luo and Tiecheng Sun and Weizhe Zhang",

note = "Publisher Copyright: {\textcopyright} 2005-2012 IEEE.",

year = "2025",

doi = "10.1109/TIFS.2025.3551640",

language = "英语",

volume = "20",

pages = "3907--3908",

journal = "IEEE Transactions on Information Forensics and Security",

issn = "1556-6013",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Vulnerabilities of NSPFL

T2 - Privacy-Preserving Federated Learning With Data Integrity Auditing

AU - Wu, Jiahui

AU - Luo, Fucai

AU - Sun, Tiecheng

AU - Zhang, Weizhe

PY - 2025

Y1 - 2025

N2 - The secure and privacy-preserving federated learning scheme, NSPFL, aims to safeguard data privacy while also auditing data integrity. The solution provided by this scheme is highly novel. However, NSPFL has significant design shortcomings in terms of both privacy protection and data integrity verification. This work identifies specific issues within NSPFL and proposes effective countermeasures. Furthermore, our proposed solution can serve as a general approach for privacy-preserving multiparty computations, safeguarding privacy while enhancing efficiency.

AB - The secure and privacy-preserving federated learning scheme, NSPFL, aims to safeguard data privacy while also auditing data integrity. The solution provided by this scheme is highly novel. However, NSPFL has significant design shortcomings in terms of both privacy protection and data integrity verification. This work identifies specific issues within NSPFL and proposes effective countermeasures. Furthermore, our proposed solution can serve as a general approach for privacy-preserving multiparty computations, safeguarding privacy while enhancing efficiency.

KW - Privacy protection

KW - data integrity auditing

KW - federated learning (FL)

KW - vulnerabilities

UR - https://www.scopus.com/pages/publications/105003027156

U2 - 10.1109/TIFS.2025.3551640

DO - 10.1109/TIFS.2025.3551640

M3 - 文章

AN - SCOPUS:105003027156

SN - 1556-6013

VL - 20

SP - 3907

EP - 3908

JO - IEEE Transactions on Information Forensics and Security

JF - IEEE Transactions on Information Forensics and Security

ER -

Vulnerabilities of NSPFL: Privacy-Preserving Federated Learning With Data Integrity Auditing

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this