TU Darmstadt / ULB / TUbiblio

Comments on “Privacy-Enhanced Federated Learning Against Poisoning Adversaries”

Schneider, Thomas ; Suresh, Ajith ; Yalame, Hossein (2023)
Comments on “Privacy-Enhanced Federated Learning Against Poisoning Adversaries”.
In: IEEE Transactions on Information Forensics and Security, 18
doi: 10.1109/TIFS.2023.3238544
Article, Bibliographie

Abstract

Liu et al. (2021) recently proposed a privacy-enhanced framework named PEFL to efficiently detect poisoning behaviours in Federated Learning (FL) using homomorphic encryption. In this article, we show that PEFL does not preserve privacy. In particular, we illustrate that PEFL reveals the entire gradient vector of all users in clear to one of the participating entities, thereby violating privacy. Furthermore, we clearly show that an immediate fix for this issue is still insufficient to achieve privacy by pointing out multiple flaws in the proposed system.

Item Type: Article
Erschienen: 2023
Creators: Schneider, Thomas ; Suresh, Ajith ; Yalame, Hossein
Type of entry: Bibliographie
Title: Comments on “Privacy-Enhanced Federated Learning Against Poisoning Adversaries”
Language: English
Date: 20 January 2023
Publisher: IEEE
Journal or Publication Title: IEEE Transactions on Information Forensics and Security
Volume of the journal: 18
DOI: 10.1109/TIFS.2023.3238544
URL / URN: https://ieeexplore.ieee.org/document/10023534
Abstract:

Liu et al. (2021) recently proposed a privacy-enhanced framework named PEFL to efficiently detect poisoning behaviours in Federated Learning (FL) using homomorphic encryption. In this article, we show that PEFL does not preserve privacy. In particular, we illustrate that PEFL reveals the entire gradient vector of all users in clear to one of the participating entities, thereby violating privacy. Furthermore, we clearly show that an immediate fix for this issue is still insufficient to achieve privacy by pointing out multiple flaws in the proposed system.

Uncontrolled Keywords: Engineering, E4, Cryptography and Privacy Engineering (ENCRYPTO), GRK Privacy&Trust for Mobile Users (Project A.1)
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Cryptography and Privacy Engineering (ENCRYPTO)
DFG-Collaborative Research Centres (incl. Transregio)
DFG-Collaborative Research Centres (incl. Transregio) > Collaborative Research Centres
Profile Areas
Profile Areas > Cybersecurity (CYSEC)
DFG-Collaborative Research Centres (incl. Transregio) > Collaborative Research Centres > CRC 1119: CROSSING – Cryptography-Based Security Solutions: Enabling Trust in New and Next Generation Computing Environments
Date Deposited: 21 Mar 2023 10:07
Last Modified: 21 Mar 2023 10:07
PPN:
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details