mlsanityData to 7 Oct 2026

Flamingo: Multi-Round Single-Server Secure Aggregation with Applications to Private Federated Learning

arXiv 2308.09883 ↗First posted 19 Aug 2023cs.CR cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

This paper introduces Flamingo, a system for secure aggregation of data across a large set of clients. In secure aggregation, a server sums up the private inputs of clients and obtains the result without learning anything about the individual inputs beyond what is implied by the final sum. Flamingo focuses on the multi-round setting found in federated learning in which many consecutive summations (averages) of model weights are performed to derive a good model. Previous protocols, such as Bell et al. (CCS '20), have been designed for a single round and are adapted to the federated learning setting by repeating the protocol multiple times. Flamingo eliminates the need for the per-round setup of previous protocols, and has a new lightweight dropout resilience protocol to ensure that if clients leave in the middle of a sum the server can still obtain a meaningful result. Furthermore, Flamingo introduces a new way to locally choose the so-called client neighborhood introduced by Bell et al. These techniques help Flamingo reduce the number of interactions between clients and the server, resulting in a significant reduction in the end-to-end runtime for a full training session over prior work. We implement and evaluate Flamingo and show that it can securely train a neural network on the (Extended) MNIST and CIFAR-100 datasets, and the model converges without a loss in accuracy, compared to a non-private federated learning system.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 20 of its 101 references that are in the map. First posted on arXiv 19 Aug 2023.

Builds on

20 of 101 references.

References · 20

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2019Deep Leakage from Gradientscited by 1,004
  4. 2018LEAF: A Benchmark for Federated Settingscited by 780
  5. 2018How To Backdoor Federated Learningcited by 745
  6. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  7. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 208
  8. 2020Federated Accelerated Stochastic Gradient Descentcited by 85
  9. 2020Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learningcited by 78
  10. 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 66
  11. 2021LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learningcited by 63
  12. 2020FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learningcited by 60
8 more
  1. 2017Prio: Private, Robust, and Scalable Computation of Aggregate Statisticscited by 35
  2. 2019Eavesdrop the Composition Proportion of Training Labels in Federated Learningcited by 27
  3. 2021EIFFeL: Ensuring Integrity for Federated Learningcited by 26
  4. 2021RoFL: Robustness of Secure Federated Learningcited by 23
  5. 2021Efficient Differentially Private Secure Aggregation for Federated Learning via Hardness of Learning with Errorscited by 23
  6. 2022How Much Privacy Does Federated Learning with Secure Aggregation Guarantee?cited by 19
  7. 2020Lightweight Techniques for Private Heavy Hitterscited by 13
  8. 2015Efficient Private Statistics with Succinct Sketchescited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 5; 2025: 5; 2026: 4.

16 papers.

Sort:

  1. 2023Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstructioncited by 18
  2. 2025TAPFed: Threshold Secure Aggregation for Privacy-Preserving Federated Learningcited by 4
  3. 2024DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning Based on Constant-Overhead Linear Secret Resharingcited by 3
  4. 2024Communication-Efficient Secure Aggregation in Decentralized Learningcited by 2
  5. 2024Uncovering Attacks and Defenses in Secure Aggregation for Federated Deep Learningcited by 2
  6. 2024On the Conflict of Robustness and Learning in Collaborative Machine Learningcited by 1
  7. 2025FedPoP: Federated Learning Meets Proof of Participationcited by 1
  8. 2026Secure Aggregation for Privacy-Preserving Federated Learning on Clinical EEG Datacited by 1
  9. 2023EASTER: Embedding Aggregation-based Heterogeneous Models Training in Vertical Federated Learningcited by 0
  10. 2024Fluent: Round-efficient Secure Aggregation for Private Federated Learningcited by 0
  11. 2025Setup Once, Secure Always: A Single-Setup Secure Federated Learning Aggregation Protocol with Forward and Backward Secrecy for Dynamic Userscited by 0
  12. 2025Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Modelscited by 0
4 more
  1. 2025On Balancing Sparsity with Reliable Connectivity in Distributed Network Design with Random K-out Graphscited by 0
  2. 2026TAPAS: Efficient Two-Server Asymmetric Private Aggregation Beyond Prio(+)cited by 0
  3. 2026Secure and Privacy-Preserving Vertical Federated Learningcited by 0
  4. 2026DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learningcited by 0