Comments on "Privacy-Enhanced Federated Learning Against Poisoning Adversaries"
This paper is significant for the federated learning community, as it corrects a critical misunderstanding regarding the privacy guarantees of a widely cited framework, preventing the continued adoption of a flawed algorithm.
This paper re-evaluates the PEFL framework, originally proposed by Liu et al. (IEEE TIFS'21) for privacy-enhanced federated learning, and demonstrates that it fails to preserve privacy by revealing the entire gradient vector of all users to a participating entity. The authors further show that even an immediate fix for this issue is insufficient, identifying multiple additional flaws in the system.
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.