[Resource Topic] 2024/1504: Comments on "Privacy-Enhanced Federated Learning Against Poisoning Adversaries"

Welcome to the resource topic for 2024/1504

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

Authors: Thomas Schneider, Ajith Suresh, Hossein Yalame

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.

ePrint: https://eprint.iacr.org/2024/1504

See all topics related to this paper.

Feel free to post resources that are related to this paper below.

Example resources include: implementations, explanation materials, talks, slides, links to previous discussions on other websites.

For more information, see the rules for Resource Topics .