Skip to content
DraconiticResearch
Search Sources API
190,332 studies31 sourcesUpdated just now
PreprintarXiv licencearXiv

Progressive-Resolution Secure Aggregation for Federated Learning

Abstract

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.

Related

  1. Fundamental Limits of Information-Theoretic Secure Aggregation with User Dropouts in Federated Learning
    Jinbao Zhu, Kai Wan, Giuseppe Caire
    arXivPreprintarXiv licenceFull textGeneral mathematicsarXiv
  2. FedPGT: Progressive Gradient Transmission for Vehicular Federated Learning over Time-Varying Channels
    Jintao Yan, Tan Chen, Yuxuan Sun +2
    arXivPreprintarXiv licenceFull textGeneral mathematicsarXiv
  3. Information-Theoretic Secure Aggregation With Heterogeneous Client Quantization
    Shreya Meel, Sennur Ulukus, Itzhak Tamo
    arXivPreprintarXiv licenceFull textGeneral mathematicsarXiv
  4. SILMARILS-MV: Information-Theoretically Secure Multi-Verifier Signatures with Dealer-Free Key Issuance and Linear Aggregation for Permissioned Blockchains
    Khadijeh Bagheri, Hassan Khodaiemehr, Chen Feng
    arXivPreprintCC BY-NC-ND 4.0Full textGeneral mathematicsQuantum physics & quantum informationarXiv
  5. Efficient Joint Trajectory Optimization and Resource Allocation for Secure UAV Networks: A Deep Reinforcement Learning Approach
    Abdulmalik Alwarafy, Mohamed Hayajneh, Mustafa Al Juboori +4
    arXivPreprintCC BY 4.0Full textGeneral mathematicsarXiv
BibTeX
@misc{azimiabarghouyi2026progressiveresolution,
  title = {{Progressive-Resolution Secure Aggregation for Federated Learning}},
  author = {Seyed Mohammad Azimi-Abarghouyi},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.00695},
  eprint = {2610.00695},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.00695},
}
RIS
TY  - UNPB
TI  - Progressive-Resolution Secure Aggregation for Federated Learning
AU  - Seyed Mohammad Azimi-Abarghouyi
PY  - 2026
DA  - 2026/10/01
PB  - arXiv
DO  - 10.48550/arxiv.2610.00695
UR  - https://arxiv.org/abs/2610.00695
AB  - 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.
ER  -