Paper 2023/486

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

Yiping Ma, University of Pennsylvania
Jess Woods, University of Pennsylvania
Sebastian Angel, University of Pennsylvania, Microsoft Research
Antigoni Polychroniadou, J.P. Morgan AI Research, J.P. Morgan AlgoCRYPT CoE
Tal Rabin, University of Pennsylvania

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.

Available format(s)
Publication info
Published elsewhere. IEEE S&P (Oakland) 2023
secure aggregationfederated learning
Contact author(s)
yipingma @ seas upenn edu
woodsjk @ seas upenn edu
sebastian angel @ cis upenn edu
antigonipoly @ gmail com
talr @ seas upenn edu
2023-05-27: last of 4 revisions
2023-04-04: received
See all versions
Short URL
Creative Commons Attribution


      author = {Yiping Ma and Jess Woods and Sebastian Angel and Antigoni Polychroniadou and Tal Rabin},
      title = {Flamingo: Multi-Round Single-Server Secure Aggregation with Applications to Private Federated Learning},
      howpublished = {Cryptology ePrint Archive, Paper 2023/486},
      year = {2023},
      note = {\url{}},
      url = {}
Note: In order to protect the privacy of readers, does not use cookies or embedded third party content.