Comments on “APFed: Anti-Poisoning Attacks in Privacy-Preserving Heterogeneous Federated Learning”
Abstract
In IEEE TIFS 2023, Chen et al. proposed a method called APFed, which leverages additive homomorphic encryption to encrypt each client’s gradient, aiming to prevent information leakage while effectively defending against poisoning attacks. In this paper, we demonstrate a fundamental flaw in the authors’ claim of security proof yielding that the proposed APFed method is insecure.
Fields of Study & Subjects
Privacy-Preserving Technologies in Data
Adversarial Robustness in Machine Learning
Cryptography and Data Security
Publication details
- Journal / source
- IEEE Transactions on Information Forensics and Security
- Volume
- 21
- Pages
- 3479–3480
- Publication date
- 1 January 2026
- Language
- EN