Metraipolis › archive › dc_ea1aa2a8fe9c
Robust and Private Swarm Learning via Zero-Knowledge Validator Admission and Consensus Aggregation — arXiv:2611.11477
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.11477
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:43:25.253Z
- SHA-256 of the archived text
5c78ad906225fea48b1c5bf880b0ed19f63cfff859a65bf3fb29de8e05e5dd02- Stable URL of this page
https://metraipolis.com/documento/dc_ea1aa2a8fe9c
How to cite
Robust and Private Swarm Learning via Zero-Knowledge Validator Admission and Consensus Aggregation — arXiv:2611.11477 — arXiv (en), https://arxiv.org/abs/2611.11477 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea1aa2a8fe9c (Metraipolis archive dc_ea1aa2a8fe9c, sha256 5c78ad906225fea48b1c5bf880b0ed19f63cfff859a65bf3fb29de8e05e5dd02)
BibTeX
@misc{dcea1aa2a8fe9c,
title = {Robust and Private Swarm Learning via Zero-Knowledge Validator Admission and Consensus Aggregation — arXiv:2611.11477},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.11477},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea1aa2a8fe9c; sha256 5c78ad906225fea48b1c5bf880b0ed19f63cfff859a65bf3fb29de8e05e5dd02},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.11477. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Swarm Learning improves resilience and removes the need for a single trusted coordinator by distributing model aggregation and validation across participating nodes. However, it also delegates the validation of model updates to peers whose private data may be biased, unrepresentative, or adversarial, and existing Swarm Learning protocols generally do not attest that data, leaving decentralized validation as an attack surface. We present a robust, privacy-preserving Swarm Learning framework that makes verifiable data quality the condition for admission to the learning task. A validator joins only after a zero-knowledge attestation proves, without revealing any raw sample, that a reference model ran correctly on its private data. The attested outputs also yield a label-free class profile, so the network assembles a collectively IID validator pool from individually skewed validators as accurately as an oracle with the true labels (total-variation distance to uniform 0.025, against 0.021 for the oracle and 0.21 for random selection). Admitted validators score client updates and, through a Tendermint-style Byzantine Fault Tolerant consensus, agree on a gradient mask and a quality-derived aggregation weight for each submission, replacing dataset-size weighting with a quality-aware signal. Adapting the cut-layer idea of Split Learning, a challenge-based audit lets peers re-verify that a mask was computed on the attested data without an expensive end-to-end zero-knowledge proof. Across four benchmarks under non-IID partitions the framework matches FedAvg on clean data; under a gradient-scaling attack that collapses FedAvg to random chance, it retains 94% of clean accuracy on CIFAR-100 and over 99% on FashionMNIST, where FedAvg achieves only 2.1% and 11%. The result is a private, robust, and auditable foundation for decentralized learning. 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); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.11477 — 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 2026-11-10T18:37:37.643Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).