mlsanityData to 14 Oct 2026

Scalable and Private Federated Learning Using Distributed Differential Privacy and Secure Aggregation

arXiv 2604.07125 ↗First posted 8 Apr 2026cs.CR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

This article presents DDP-SA, a scalable privacy-preserving federated learning framework that jointly leverages client-side local differential privacy (LDP) and full-threshold additive secret sharing (ASS) for secure aggregation. Unlike existing methods that rely solely on differential privacy or on secure multi-party computation (MPC), DDP-SA integrates both techniques to deliver stronger end-to-end privacy guarantees while remaining computationally practical. The framework introduces a two-stage protection mechanism: clients first perturb their local gradients with calibrated Laplace noise, then decompose the noisy gradients into additive secret shares that are distributed across multiple intermediate servers. This design ensures that (i) no single compromised server or communication channel can reveal any information about individual client updates, and (ii) the parameter server reconstructs only the aggregated noisy gradient, never any client-specific contribution. Extensive experiments show that DDP-SA achieves substantially higher model accuracy than standalone LDP while providing stronger privacy protection than MPC-only approaches. The proposed framework scales linearly with the number of participants and offers a practical, privacy-preserving solution for federated learning applications with controllable computational and communication overhead.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 61 of its 106 references that are in the map. First posted on arXiv 8 Apr 2026.

Builds on

61 of 106 references.

References · 61

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2019Deep Leakage from Gradientscited by 1,021
  4. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  5. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 520
  6. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  7. 2020iDLG: Improved Deep Leakage from Gradientscited by 382
  8. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 348
  9. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 334
  10. 2014RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Responsecited by 272
  11. 2018Scalable Private Learning with PATEcited by 269
  12. 2019Differentially Private Learning with Adaptive Clippingcited by 220
38 more
  1. 2017Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryptioncited by 176
  2. 2018cpSGD: Communication-efficient and differentially-private distributed SGDcited by 158
  3. 2017Collecting Telemetry Data Privatelycited by 149
  4. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 132
  5. 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 128
  6. 2019Secure Federated Matrix Factorizationcited by 102
  7. 2020Privacy Preserving Vertical Federated Learning for Tree-based Modelscited by 89
  8. 2020VAFL: a Method of Vertical Asynchronous Federated Learningcited by 87
  9. 2020Local and Central Differential Privacy for Robustness and Privacy in Federated Learningcited by 78
  10. 2020Local Differential Privacy based Federated Learning for Internet of Thingscited by 75
  11. 2021Differentially Private Federated Learning on Heterogeneous Datacited by 74
  12. 2021Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacycited by 69
  13. 2021The Skellam Mechanism for Differentially Private Federated Learningcited by 68
  14. 2020LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacycited by 64
  15. 2019Federated Learning with Bayesian Differential Privacycited by 60
  16. 2020Wireless Federated Learning with Local Differential Privacycited by 52
  17. 2019HybridAlpha: An Efficient Approach for Privacy-Preserving Federated Learningcited by 51
  18. 2019Collecting and Analyzing Multidimensional Data with Local Differential Privacycited by 49
  19. 2018DP-ADMM: ADMM-based Distributed Learning with Differential Privacycited by 42
  20. 2020Federated Model Distillation with Noise-Free Differential Privacycited by 40
  21. 2022The Fundamental Price of Secure Aggregation in Differentially Private Federated Learningcited by 39
  22. 2020FedSel: Federated SGD under Local Differential Privacy with Top-k Dimension Selectioncited by 36
  23. 2022Differentially Private Federated Learning with Local Regularization and Sparsificationcited by 36
  24. 2022SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compressioncited by 34
  25. 2023Make Landscape Flatter in Differentially Private Federated Learningcited by 33
  26. 2021Federated f-Differential Privacycited by 29
  27. 2020FLAME: Differentially Private Federated Learning in the Shuffle Modelcited by 27
  28. 2020FederBoost: Private Federated Learning for GBDTcited by 27
  29. 2021Efficient Differentially Private Secure Aggregation for Federated Learning via Hardness of Learning with Errorscited by 25
  30. 2022Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learningcited by 23
  31. 2022Learning to Generate Image Embeddings with User-level Differential Privacycited by 23
  32. 2023Practical Differentially Private and Byzantine-resilient Federated Learningcited by 18
  33. 2020Compression Boosts Differentially Private Federated Learningcited by 13
  34. 2022Differentially Private CutMix for Split Learning with Vision Transformercited by 13
  35. 2022Adap DP-FL: Differentially Private Federated Learning with Adaptive Noisecited by 13
  36. 2022OpBoost: A Vertical Federated Tree Boosting Framework Based on Order-Preserving Desensitizationcited by 12
  37. 2021Differentially Private Federated Learning via Inexact ADMMcited by 11
  38. 2024Cross-silo Federated Learning with Record-level Personalized Differential Privacycited by 9

50 most cited of 61 All 61 (JSON)

Built on by

Not cited yet.