Metraipolis › archive › dc_f48577d4d276
FedSumUp: User-Auditable Privacy-Aware Representation Sharing for Resource-Constrained Federated Intelligence — arXiv:2610.21194
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.21194
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T09:14:21.643Z
- SHA-256 of the archived text
f9355377bbadd38237eb7cf3300265a10cd1ab59afe25a9a7a28255407e26937- Stable URL of this page
https://metraipolis.com/documento/dc_f48577d4d276
How to cite
FedSumUp: User-Auditable Privacy-Aware Representation Sharing for Resource-Constrained Federated Intelligence — arXiv:2610.21194 — arXiv (en), https://arxiv.org/abs/2610.21194 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f48577d4d276 (Metraipolis archive dc_f48577d4d276, sha256 f9355377bbadd38237eb7cf3300265a10cd1ab59afe25a9a7a28255407e26937)
BibTeX
@misc{dcf48577d4d276,
title = {FedSumUp: User-Auditable Privacy-Aware Representation Sharing for Resource-Constrained Federated Intelligence — arXiv:2610.21194},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.21194},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f48577d4d276; sha256 f9355377bbadd38237eb7cf3300265a10cd1ab59afe25a9a7a28255407e26937},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21194. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Existing federated data condensation methods face privacy risks, as uploaded synthetic data may preserve sensitive information and remain vulnerable to reconstruction attacks. Moreover, their generation often incurs considerable client-side computational overhead, limiting deployment on resource-constrained devices. To address these issues, we propose FedSumUp, which employs a learnable lossy compressor on clients to generate compact and visually interpretable representations. By controlling information capacity, FedSumUp reduces privacy leakage while allowing users to directly assess the privacy-utility tradeoff. We further introduce a dual-objective optimization mechanism to preserve task-relevant semantics while suppressing reconstruction risks. The compressor is trained on the server and only performs lightweight inference on clients. Since the server cannot access raw data, we develop a data-free closed-loop optimization strategy that optimizes the compressor by minimizing the discrepancy between original and twice-compressed representations after structure-preserving upsampling. Experiments on BloodMNIST, CIFAR-10, and ChestMNIST demonstrate reconstruction PSNR as low as 8.56 dB (with synthetic PSNR as low as 5.45 dB), client runtime reductions up to 96.5% (from 778s to 27s on ChestMNIST), and competitive classification accuracy (89.72% ChestMNIST, 82.24% BloodMNIST, 65.63% CIFAR-10), while remaining inherently robust to non-IID data distributions. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.21194 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T08:44:17.919Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).