Paper 2024/1504 Original: eprint.iacr.org/2024/1504 ↗
Comments on "Privacy-Enhanced Federated Learning Against Poisoning Adversaries"
Abstract
In August 2021, Liu et al. (IEEE TIFS'21) 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.
Metadata
- Available format(s)
PDF- Category
- Cryptographic protocols
- Publication info
- Preprint.
- History
- 2024-09-25: last updated
- 2024-09-25: published
- Short URL
- https://ia.cr/2024/1504
- License
- https://creativecommons.org/licenses/by-sa/4.0/
BibTeX
@misc{cryptoeprint:2024/1504,
author = {Thomas Schneider and Ajith Suresh and Hossein Yalame},
title = {Comments on "Privacy-Enhanced Federated Learning Against Poisoning Adversaries"},
howpublished = {Cryptology {ePrint} Archive, Paper 2024/1504},
year = {2024},
url = {https://eprint.iacr.org/2024/1504}
}