mlsanityData to 14 Oct 2026

Towards Trustworthy Federated Learning with Untrusted Participants

arXiv 2505.01874 ↗First posted 3 May 2025cs.LG cs.CR cs.DCcited by 8

Not on the map. Why?

Abstract (arXiv)

Resilience against malicious participants and data privacy are essential for trustworthy federated learning, yet achieving both with good utility typically requires the strong assumption of a trusted central server. This paper shows that a significantly weaker assumption suffices: each pair of participants shares a randomness seed unknown to others. In a setting where malicious participants may collude with an untrusted server, we propose CafCor, an algorithm that integrates robust gradient aggregation with correlated noise injection, using shared randomness between participants. We prove that CafCor achieves strong privacy-utility trade-offs, significantly outperforming local differential privacy (DP) methods, which do not make any trust assumption, while approaching central DP utility, where the server is fully trusted. Empirical results on standard benchmarks validate CafCor's practicality, showing that privacy and robustness can coexist in distributed systems without sacrificing utility or trusting the server.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 42 of its 73 references that are in the map. First posted on arXiv 3 May 2025.

Builds on

42 of 73 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2019Advances and Open Problems in Federated Learningcited by 3,046
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  5. 2019Deep Leakage from Gradientscited by 1,021
  6. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  7. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  8. 2016Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Lojasiewicz Conditioncited by 539
  9. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 520
  10. 2021Opacus: User-Friendly Differential Privacy Library in PyTorchcited by 383
  11. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 334
  12. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 288
30 more
  1. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 246
  2. 2018Amplification by Shuffling: From Local to Central Differential Privacy via Anonymitycited by 164
  3. 2018cpSGD: Communication-efficient and differentially-private distributed SGDcited by 158
  4. 2019Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulationcited by 141
  5. 2020Learning from History for Byzantine Robust Optimizationcited by 137
  6. 2020Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcited by 128
  7. 2018Distributed Differential Privacy via Shufflingcited by 115
  8. 2016Minimax Optimal Procedures for Locally Private Estimationcited by 107
  9. 2023Stochastic Controlled Averaging for Federated Learning with Communication Compressioncited by 101
  10. 2018Generalized Byzantine-tolerant SGDcited by 95
  11. 2017Being Robust (in High Dimensions) Can Be Practicalcited by 83
  12. 2021Differentially Private Federated Learning on Heterogeneous Datacited by 74
  13. 2021Robust and Differentially Private Mean Estimationcited by 66
  14. 2023Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneitycited by 65
  15. 2022Byzantine Machine Learning Made Easy by Resilient Averaging of Momentumscited by 63
  16. 2020Byzantine-Resilient Non-Convex Stochastic Gradient Descentcited by 57
  17. 2021Efficient Mean Estimation with Pure Differential Privacy via a Sum-of-Squares Exponential Mechanismcited by 50
  18. 2019Differential Privacy-enabled Federated Learning for Sensitive Health Datacited by 44
  19. 2017Resilience: A Criterion for Learning in the Presence of Arbitrary Outlierscited by 43
  20. 2019Manipulation Attacks in Local Differential Privacycited by 28
  21. 2023Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneitycited by 26
  22. 2023On the Privacy-Robustness-Utility Trilemma in Distributed Learningcited by 24
  23. 2020An Accurate, Scalable and Verifiable Protocol for Federated Differentially Private Averagingcited by 20
  24. 2020Robust estimation via generalized quasi-gradientscited by 19
  25. 2021Differential Privacy and Byzantine Resilience in SGD: Do They Add Up?cited by 18
  26. 2024The Privacy Power of Correlated Noise in Decentralized Learningcited by 18
  27. 2022Bridging Differential Privacy and Byzantine-Robustness via Model Aggregationcited by 13
  28. 2022Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attackscited by 12
  29. 2023DP-BREM: Differentially-Private and Byzantine-Robust Federated Learning with Client Momentumcited by 6
  30. 2021Robust Testing and Estimation under Manipulation Attackscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 6.

8 papers.

  1. 2025ByzFL: Research Framework for Robust Federated Learningcited by 4
  2. 2025Tight Stability Bounds for Robust Distributed Learning: Byzantine Failures Hurt Generalization More than Data Poisoningcited by 2
  3. 2026SoK: Enhancing Cryptographic Collaborative Learning with Differential Privacycited by 0
  4. 2026From Inexact Gradients to Byzantine Robustness: Acceleration and Optimization under Similaritycited by 0
  5. 2026SecureGate: Learning When to Reveal PII Safely via Token-Gated Dual-Adapters for Federated LLMscited by 0
  6. 2026Practical Validity Conditions for Byzantine-Tolerant Federated Learningcited by 0
  7. 2026Dangerous Liaisons of Convex Learning and Non-Affine Aggregationcited by 0
  8. 2026Unveiling the Non-Monotonic Effect of Privacy on Generalization under Byzantine Robustnesscited by 0