mlsanityData to 7 Oct 2026

FheFL: Fully Homomorphic Encryption Friendly Privacy-Preserving Federated Learning with Byzantine Users

arXiv 2306.05112 ↗First posted 8 Jun 2023cs.AI cs.CRcited by 3

Not on the map. Why?

Abstract (arXiv)

The federated learning (FL) technique was developed to mitigate data privacy issues in the traditional machine learning paradigm. While FL ensures that a user's data always remain with the user, the gradients are shared with the centralized server to build the global model. This results in privacy leakage, where the server can infer private information from the shared gradients. To mitigate this flaw, the next-generation FL architectures proposed encryption and anonymization techniques to protect the model updates from the server. However, this approach creates other challenges, such as malicious users sharing false gradients. Since the gradients are encrypted, the server is unable to identify rogue users. To mitigate both attacks, this paper proposes a novel FL algorithm based on a fully homomorphic encryption (FHE) scheme. We develop a distributed multi-key additive homomorphic encryption scheme that supports model aggregation in FL. We also develop a novel aggregation scheme within the encrypted domain, utilizing users' non-poisoning rates, to effectively address data poisoning attacks while ensuring privacy is preserved by the proposed encryption scheme. Rigorous security, privacy, convergence, and experimental analyses have been provided to show that FheFL is novel, secure, and private, and achieves comparable accuracy at reasonable computational cost.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 18 of its 41 references that are in the map. First posted on arXiv 8 Jun 2023.

Builds on

18 of 41 references.

References · 18

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  3. 2019Deep Leakage from Gradientscited by 1,004
  4. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  5. 2020iDLG: Improved Deep Leakage from Gradientscited by 367
  6. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  7. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 266
  8. 2020Byzantine-Resilient Secure Federated Learningcited by 93
  9. 2020Local Differential Privacy based Federated Learning for Internet of Thingscited by 74
  10. 2021TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryptioncited by 51
  11. 2021Privacy-preserving Federated Learning based on Multi-key Homomorphic Encryptioncited by 46
  12. 2022FLCert: Provably Secure Federated Learning against Poisoning Attackscited by 29
6 more
  1. 2020Robust Aggregation for Adaptive Privacy Preserving Federated Learning in Healthcarecited by 18
  2. 2023Efficient Secure Aggregation for Privacy-Preserving Federated Machine Learningcited by 7
  3. 2023Recursive Euclidean Distance Based Robust Aggregation Technique For Federated Learningcited by 4
  4. 2022Enhanced Security and Privacy via Fragmented Federated Learningcited by 3
  5. 2022MUD-PQFed: Towards Malicious User Detection in Privacy-Preserving Quantized Federated Learningcited by 2
  6. 2020Scalar Product Lattice Computation for Efficient Privacy-preserving Systemscited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 1.

3 papers.

  1. 2024MQFL-FHE: Multimodal Quantum Federated Learning Framework with Fully Homomorphic Encryptioncited by 7
  2. 2023SABLE: Secure And Byzantine robust LEarningcited by 0
  3. 2025VFEFL: Privacy-Preserving Federated Learning against Malicious Clients via Verifiable Functional Encryptioncited by 0