mlsanityData to 7 Oct 2026

ScionFL: Efficient and Robust Secure Quantized Aggregation

arXiv 2210.07376 ↗First posted 13 Oct 2022cs.CR cs.IT cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Secure aggregation is commonly used in federated learning (FL) to alleviate privacy concerns related to the central aggregator seeing all parameter updates in the clear. Unfortunately, most existing secure aggregation schemes ignore two critical orthogonal research directions that aim to (i) significantly reduce client-server communication and (ii) mitigate the impact of malicious clients. However, both of these additional properties are essential to facilitate cross-device FL with thousands or even millions of (mobile) participants. In this paper, we unite both research directions by introducing ScionFL, the first secure aggregation framework for FL that operates efficiently on quantized inputs and simultaneously provides robustness against malicious clients. Our framework leverages (novel) multi-party computation (MPC) techniques and supports multiple linear (1-bit) quantization schemes, including ones that utilize the randomized Hadamard transform and Kashin's representation. Our theoretical results are supported by extensive evaluations. We show that with no overhead for clients and moderate overhead for the server compared to transferring and processing quantized updates in plaintext, we obtain comparable accuracy for standard FL benchmarks. Moreover, we demonstrate the robustness of our framework against state-of-the-art poisoning attacks.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 64 of its 155 references that are in the map. First posted on arXiv 13 Oct 2022.

Builds on

64 of 155 references.

References · 64

  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. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  5. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  6. 2018How To Backdoor Federated Learningcited by 745
  7. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  8. 2018signSGD: Compressed Optimisation for Non-Convex Problemscited by 561
  9. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  10. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  11. 2018Sparsified SGD with Memorycited by 373
  12. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
38 more
  1. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 330
  2. 2021A Field Guide to Federated Optimizationcited by 312
  3. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 285
  4. 2017TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learningcited by 253
  5. 2019Can You Really Backdoor Federated Learning?cited by 250
  6. 2017Sparse Communication for Distributed Gradient Descentcited by 243
  7. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
  8. 2018The Convergence of Sparsified Gradient Methodscited by 228
  9. 2018Gazelle: A Low Latency Framework for Secure Neural Network Inferencecited by 193
  10. 2020FetchSGD: Communication-Efficient Federated Learning with Sketchingcited by 178
  11. 2018Expanding the Reach of Federated Learning by Reducing Client Resource Requirementscited by 162
  12. 2018RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasetscited by 148
  13. 2020On Biased Compression for Distributed Learningcited by 140
  14. 2016Distributed Mean Estimation with Limited Communicationcited by 134
  15. 2021EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedbackcited by 131
  16. 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 126
  17. 2022FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clientscited by 119
  18. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 116
  19. 2021Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Modelscited by 106
  20. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 97
  21. 2018Is feature selection secure against training data poisoning?cited by 88
  22. 2019Communication-efficient distributed SGD with Sketchingcited by 81
  23. 2020Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learningcited by 78
  24. 20211-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speedcited by 74
  25. 2022Fishing for User Data in Large-Batch Federated Learning via Gradient Magnificationcited by 72
  26. 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 66
  27. 2017Knock Knock, Who's There? Membership Inference on Aggregate Location Datacited by 63
  28. 2020FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learningcited by 60
  29. 2021EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learningcited by 53
  30. 2020BaFFLe: Backdoor detection via Feedback-based Federated Learningcited by 52
  31. 2021DRIVE: One-bit Distributed Mean Estimationcited by 52
  32. 2019XONN: XNOR-based Oblivious Deep Neural Network Inferencecited by 51
  33. 2020Uncertainty Principle for Communication Compression in Distributed and Federated Learning and the Search for an Optimal Compressorcited by 45
  34. 2021Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrixcited by 43
  35. 2022The Fundamental Price of Secure Aggregation in Differentially Private Federated Learningcited by 39
  36. 2021Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learningcited by 38
  37. 2017Prio: Private, Robust, and Scalable Computation of Aggregate Statisticscited by 35
  38. 2020Stochastic-Sign SGD for Federated Learning with Theoretical Guaranteescited by 34

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 2; 2026: 2.

8 papers.

  1. 2024SoK: Blockchain-Based Decentralized AI (DeAI)cited by 6
  2. 2026Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Provencited by 4
  3. 2024LoByITFL: Low Communication Secure and Private Federated Learningcited by 3
  4. 2023WW-FL: Secure and Private Large-Scale Federated Learningcited by 2
  5. 2024Fluent: Round-efficient Secure Aggregation for Private Federated Learningcited by 0
  6. 2025SLVR: Securely Leveraging Client Validation for Robust Federated Learningcited by 0
  7. 2025Perfect Privacy for Discriminator-Based Byzantine-Resilient Federated Learningcited by 0
  8. 2026Progressive-Resolution Secure Aggregation for Federated Learningcited by 0