Paper 2024/1504

Comments on "Privacy-Enhanced Federated Learning Against Poisoning Adversaries"

Thomas Schneider, TU Darmstadt
Ajith Suresh, TU Darmstadt
Hossein Yalame, TU Darmstadt
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.

Note: Although our privacy issues mentioned in Section II have been published in January 2023 (Schneider et. al., IEEE TIFS'23), several subsequent papers continued to reference Liu et al. (IEEE TIFS'21) as a potential solution for private federated learning. While a few works have acknowledged the privacy concerns we raised, several of subsequent works either propagate these errors or adopt the constructions from Liu et al. (IEEE TIFS'21), thereby unintentionally inheriting the same privacy vulnerabilities. We believe this oversight is partly due to the limited visibility of our comments paper at TIFS'23 (Schneider et. al., IEEE TIFS'23). Consequently, to prevent the continued propagation of the flawed algorithms in Liu et al. (IEEE TIFS'21) into future research, we also put this article to an ePrint.

Metadata
Available format(s)
PDF
Category
Cryptographic protocols
Publication info
Published elsewhere. Minor revision. IEEE Transactions on Information Forensics and Security
DOI
10.1109/TIFS.2023.3238544
Keywords
Federated LearningFLHomomorphic EncryptionPoisoning and Inference AttacksData Privacy
Contact author(s)
schneider @ encrypto cs tu-darmstadt de
suresh @ encrypto cs tu-darmstadt de
yalame @ encrypto cs tu-darmstadt de
History
2024-09-30: approved
2024-09-25: received
See all versions
Short URL
https://ia.cr/2024/1504
License
Creative Commons Attribution-ShareAlike
CC BY-SA

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},
      doi = {10.1109/TIFS.2023.3238544},
      url = {https://eprint.iacr.org/2024/1504}
}
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.