mlsanityData to 7 Oct 2026

FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learning

arXiv 2009.11248 ↗First posted 23 Sep 2020cs.CR cs.IT cs.LGcited by 60

Not on the map. Why?

Abstract (arXiv)

Recent attacks on federated learning demonstrate that keeping the training data on clients' devices does not provide sufficient privacy, as the model parameters shared by clients can leak information about their training data. A 'secure aggregation' protocol enables the server to aggregate clients' models in a privacy-preserving manner. However, existing secure aggregation protocols incur high computation/communication costs, especially when the number of model parameters is larger than the number of clients participating in an iteration -- a typical scenario in federated learning. In this paper, we propose a secure aggregation protocol, FastSecAgg, that is efficient in terms of computation and communication, and robust to client dropouts. The main building block of FastSecAgg is a novel multi-secret sharing scheme, FastShare, based on the Fast Fourier Transform (FFT), which may be of independent interest. FastShare is information-theoretically secure, and achieves a trade-off between the number of secrets, privacy threshold, and dropout tolerance. Riding on the capabilities of FastShare, we prove that FastSecAgg is (i) secure against the server colluding with 'any' subset of some constant fraction (e.g. ~10%) of the clients in the honest-but-curious setting; and (ii) tolerates dropouts of a 'random' subset of some constant fraction (e.g. ~10%) of the clients. FastSecAgg achieves significantly smaller computation cost than existing schemes while achieving the same (orderwise) communication cost. In addition, it guarantees security against adaptive adversaries, which can perform client corruptions dynamically during the execution of the protocol.

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 11; 2023: 13; 2024: 10; 2025: 9; 2026: 6.

60 papers.

Sort:

  1. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 81
  2. 2023FedExP: Speeding Up Federated Averaging via Extrapolationcited by 68
  3. 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 66
  4. 2021LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learningcited by 63
  5. 2021Privacy-Preserving Machine Learning: Methods, Challenges and Directionscited by 58
  6. 2022The Fundamental Price of Secure Aggregation in Differentially Private Federated Learningcited by 39
  7. 2021Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learningcited by 38
  8. 2023LOKI: Large-scale Data Reconstruction Attack against Federated Learning through Model Manipulationcited by 35
  9. 2021Training Fair Models in Federated Learning without Data Privacy Infringementcited by 26
  10. 2021CodedPaddedFL and CodedSecAgg: Straggler Mitigation and Secure Aggregation in Federated Learningcited by 20
  11. 2021Information Theoretic Secure Aggregation with User Dropoutscited by 19
  12. 2022How Much Privacy Does Federated Learning with Secure Aggregation Guarantee?cited by 19
38 more
  1. 2022SwiftAgg+: Achieving Asymptotically Optimal Communication Loads in Secure Aggregation for Federated Learningcited by 18
  2. 2023Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstructioncited by 18
  3. 2022DReS-FL: Dropout-Resilient Secure Federated Learning for Non-IID Clients via Secret Data Sharingcited by 17
  4. 2023Efficient and Secure Federated Learning for Financial Applicationscited by 17
  5. 2022Aggregation Service for Federated Learning: An Efficient, Secure, and More Resilient Realizationcited by 16
  6. 2023Flamingo: Multi-Round Single-Server Secure Aggregation with Applications to Private Federated Learningcited by 16
  7. 2022Secure Aggregation for Federated Learning in Flowercited by 15
  8. 2024FedFisher: Leveraging Fisher Information for One-Shot Federated Learningcited by 15
  9. 2022SwiftAgg: Communication-Efficient and Dropout-Resistant Secure Aggregation for Federated Learning with Worst-Case Security Guaranteescited by 14
  10. 2024The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscapecited by 13
  11. 2023Federated Learning over Coupled Graphscited by 12
  12. 2021Secure Aggregation for Buffered Asynchronous Federated Learningcited by 10
  13. 2021Towards Sparse Federated Analytics: Location Heatmaps under Distributed Differential Privacy with Secure Aggregationcited by 10
  14. 2021Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategiescited by 9
  15. 2023Federated Analytics: A surveycited by 9
  16. 2022ScionFL: Efficient and Robust Secure Quantized Aggregationcited by 8
  17. 2023Byzantine-Robust Federated Learning with Variance Reduction and Differential Privacycited by 8
  18. 2025Fundamental Limits of Hierarchical Secure Aggregation with Cyclic User Associationcited by 7
  19. 2024Differentially private and decentralized randomized power methodcited by 6
  20. 2023Proof-of-Contribution-Based Design for Collaborative Machine Learning on Blockchaincited by 5
  21. 2023Private Aggregation in Hierarchical Wireless Federated Learning with Partial and Full Collusioncited by 5
  22. 2024Worldwide Federated Training of Language Modelscited by 5
  23. 2024FedStaleWeight: Buffered Asynchronous Federated Learning with Fair Aggregation via Staleness Reweightingcited by 5
  24. 2024Breaking Secure Aggregation: Label Leakage from Aggregated Gradients in Federated Learningcited by 5
  25. 2024A survey on secure decentralized optimization and learningcited by 4
  26. 2025TAPFed: Threshold Secure Aggregation for Privacy-Preserving Federated Learningcited by 4
  27. 2024Review of Mathematical Optimization in Federated Learningcited by 3
  28. 2022Local Model Reconstruction Attacks in Federated Learning and their Usescited by 2
  29. 2024FastLloyd: Federated, Accurate, Secure, and Tunable k-Means Clustering with Differential Privacycited by 2
  30. 2023AnoFel: Supporting Anonymity for Privacy-Preserving Federated Learningcited by 1
  31. 2023Privacy-Preserving Federated Learning over Vertically and Horizontally Partitioned Data for Financial Anomaly Detectioncited by 1
  32. 2024Attribute Inference Attacks for Federated Regression Taskscited by 1
  33. 2025Optimal Client Sampling in Federated Learning with Client-Level Heterogeneous Differential Privacycited by 1
  34. 2025ModShift: Model Privacy via Designed Shiftscited by 1
  35. 2026Secure Aggregation for Privacy-Preserving Federated Learning on Clinical EEG Datacited by 1
  36. 2021Practical and Light-weight Secure Aggregation for Federated Submodel Learningcited by 0
  37. 2022Secure Embedding Aggregation for Federated Representation Learningcited by 0
  38. 2023Towards Sybil Resilience in Decentralized Learningcited by 0

50 most cited of 60 All 60 (JSON)