mlsanityData to 7 Oct 2026

FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System

arXiv 2303.10837 ↗First posted 20 Mar 2023cs.LG cs.CRcited by 38

Not on the map. Why?

Abstract (arXiv)

Federated Learning trains machine learning models on distributed devices by aggregating local model updates instead of local data. However, privacy concerns arise as the aggregated local models on the server may reveal sensitive personal information by inversion attacks. Privacy-preserving methods, such as homomorphic encryption (HE), then become necessary for FL training. Despite HE's privacy advantages, its applications suffer from impractical overheads, especially for foundation models. In this paper, we present FedML-HE, the first practical federated learning system with efficient HE-based secure model aggregation. FedML-HE proposes to selectively encrypt sensitive parameters, significantly reducing both computation and communication overheads during training while providing customizable privacy preservation. Our optimized system demonstrates considerable overhead reduction, particularly for large foundation models (e.g., ~10x reduction for ResNet-50, and up to ~40x reduction for BERT), demonstrating the potential for scalable HE-based FL deployment.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 32 of its 70 references that are in the map. First posted on arXiv 20 Mar 2023.

Builds on

32 of 70 references.

References · 32

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  6. 2016Deep Learning with Differential Privacycited by 2,682
  7. 2020Adaptive Federated Optimizationcited by 1,036
  8. 2019Deep Leakage from Gradientscited by 1,004
  9. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  10. 2017Sparse Communication for Distributed Gradient Descentcited by 243
  11. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
  12. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 208
20 more
  1. 2018Sensitivity and Generalization in Neural Networks: an Empirical Studycited by 187
  2. 2020A Theory of Usable Information Under Computational Constraintscited by 153
  3. 2018ATOMO: Communication-efficient Learning via Atomic Sparsificationcited by 135
  4. 2018Protection Against Reconstruction and Its Applications in Private Federated Learningcited by 127
  5. 2016Robust Large Margin Deep Neural Networkscited by 117
  6. 2019DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compressioncited by 98
  7. 2020FedGAN: Federated Generative Adversarial Networks for Distributed Datacited by 89
  8. 2022NVIDIA FLARE: Federated Learning from Simulation to Real-Worldcited by 78
  9. 2021LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learningcited by 63
  10. 2020Differentially Private Secure Multi-Party Computation for Federated Learning in Financial Applicationscited by 58
  11. 2022Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Modelscited by 52
  12. 2022GradViT: Gradient Inversion of Vision Transformerscited by 52
  13. 2021TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryptioncited by 51
  14. 2021Privacy-preserving Federated Learning based on Multi-key Homomorphic Encryptioncited by 46
  15. 2022On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Datacited by 36
  16. 2021APRIL: Finding the Achilles' Heel on Privacy for Vision Transformerscited by 23
  17. 2020HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Datacited by 22
  18. 2020Layer-wise Characterization of Latent Information Leakage in Federated Learningcited by 19
  19. 2021Secure Neuroimaging Analysis using Federated Learning with Homomorphic Encryptioncited by 18
  20. 2021FLASHE: Additively Symmetric Homomorphic Encryption for Cross-Silo Federated Learningcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 10; 2025: 17; 2026: 7.

38 papers.

Sort:

By area:

  1. 2024Advances and Open Challenges in Federated Foundation Modelscited by 33
  2. 2024Federated Large Language Models: Current Progress and Future Directionscited by 22
  3. 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiencycited by 21
  4. 2024Federated Learning Priorities Under the European Union Artificial Intelligence Actcited by 13
  5. 2024The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscapecited by 13
  6. 2025Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generationcited by 7
  7. 2023When Federated Learning meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protectioncited by 6
  8. 2025TFHE-Coder: Evaluating LLM-agentic Fully Homomorphic Encryption Code Generationcited by 4
  9. 2025Towards Harnessing the Collaborative Power of Large and Small Models for Domain Taskscited by 4
  10. 2023Privacy Preservation in Artificial Intelligence and Extended Reality (AI-XR) Metaverses: A Surveycited by 3
  11. 2024FedGraph: A Research Library and Benchmark for Federated Graph Learningcited by 3
  12. 2025Equitable Federated Learning with NCAcited by 3
26 more
  1. 2024Dealing Doubt: Unveiling Threat Models in Gradient Inversion Attacks under Federated Learning, A Survey and Taxonomycited by 2
  2. 2024QuanCrypt-FL: Quantized Homomorphic Encryption with Pruning for Secure Federated Learningcited by 2
  3. 2025Adversarial Robustness in Distributed Quantum Machine Learningcited by 2
  4. 2025On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directionscited by 2
  5. 2025A Privacy-Preserving Federated Learning Method with Homomorphic Encryption in Omics Datacited by 2
  6. 2024Bridging Today and the Future of Humanity: AI Safety in 2024 and Beyondcited by 1
  7. 2025Enhancing Model Privacy in Federated Learning with Random Masking and Quantizationcited by 1
  8. 2025DictPFL: Efficient and Private Federated Learning on Encrypted Gradientscited by 1
  9. 2025Operator-Theoretic Framework for Gradient-Free Federated Learningcited by 1
  10. 2026CQSA: Byzantine-robust Clustered Quantum Secure Aggregation in Federated Learningcited by 1
  11. 2026Integrating Homomorphic Encryption and Synthetic Data in FL for Privacy and Learning Qualitycited by 1
  12. 2023Adversarial Predictions of Data Distributions Across Federated Internet-of-Things Devicescited by 0
  13. 2024P4: Towards private, personalized, and Peer-to-Peer learningcited by 0
  14. 2024GDBR: Label Recovery Attack Against Partial Gradient Encryption in Federated Learningcited by 0
  15. 2025CONTINUUM: Detecting APT Attacks through Spatial-Temporal Graph Neural Networkscited by 0
  16. 2025A Selective Homomorphic Encryption Approach for Faster Privacy-Preserving Federated Learningcited by 0
  17. 2025Towards Trustworthy Federated Learningcited by 0
  18. 2025Secure Generalization through Stochastic Bidirectional Parameter Updates Using Dual-Gradient Mechanismcited by 0
  19. 2025Client Clustering Meets Knowledge Sharing: Enhancing Privacy and Robustness in Personalized Peer-to-Peer Learningcited by 0
  20. 2025AnalogFed: Privacy-Preserving Discovery of Analog Circuits at Scale with Federated Generative AIcited by 0
  21. 2025Evaluating Selective Encryption Against Gradient Inversion Attackscited by 0
  22. 2026Communication-Efficient Federated AUC Maximization with Cyclic Client Participationcited by 0
  23. 2026Decentralized Privacy-Preserving Federal Learning of Computer Vision Models on Edge Devicescited by 0
  24. 2026FedBGS: A Blockchain Approach to Segment Gossip Learning in Decentralized Systemscited by 0
  25. 2026Balancing Privacy-Quality-Efficiency in Federated Learning through Round-Based Interleaving of Protection Techniquescited by 0
  26. 2026PRoVeFL: Private Robust and Verifiable Aggregation in Federated Learningcited by 0