mlsanityData to 7 Oct 2026

Progressive-Resolution Secure Aggregation for Federated Learning

arXiv 2610.00695 ↗First posted 30 Sep 2026cs.CR cs.DC cs.ITcited by 0

Not on the map. Why?

Abstract (arXiv)

Secure aggregation lets a server recover an aggregate of client updates without observing any individual update, but conventional protocols fix the aggregate precision when clients upload. We introduce and formulate a new progressive-resolution secure-aggregation functionality in which clients upload once and successively finer resolutions of the same aggregate can later be authorized without renewed client participation. To realize this functionality, we propose progressive-resolution secure aggregation (PSA): each clipped, dithered update is represented by compatible nested-lattice digits; separately releasable layers are protected by secure aggregation and an additional aggregate pad that remains unavailable to the server until a non-colluding release controller authorizes that layer.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 27 references that are in the map. First posted on arXiv 30 Sep 2026.

Builds on

13 of 27 references.

References · 13

  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. 2020The Discrete Gaussian for Differential Privacycited by 134
  4. 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 127
  5. 2020UVeQFed: Universal Vector Quantization for Federated Learningcited by 103
  6. 2021The Skellam Mechanism for Differentially Private Federated Learningcited by 66
  7. 2017Prio: Private, Robust, and Scalable Computation of Aggregate Statisticscited by 35
  8. 2022Joint Privacy Enhancement and Quantization in Federated Learningcited by 34
  9. 2022ScionFL: Efficient and Robust Secure Quantized Aggregationcited by 8
  10. 2024Federated Learning via Lattice Joint Source-Channel Codingcited by 6
  11. 2023Compressed Private Aggregation for Scalable and Robust Federated Learning over Massive Networkscited by 5
  12. 2024Compute-Update Federated Learning: A Lattice Coding Approach Over-the-Aircited by 5
1 more
  1. 2025OLALa: Online Learned Adaptive Lattice Codes for Heterogeneous Federated Learningcited by 1

Built on by

Not cited yet.