Metraipolis › archive › dc_36dd76b9541b
Trust-But-Verify: Poisoning-Resilient Locally Private Graph Learning Protocols — arXiv:2609.07063
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.07063
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:57:39.613Z
- SHA-256 of the archived text
ae12b8ed2076153c7de88d4cda3b3ba292e9a986a0fc0b0f22e532f0dd64d5ed- Stable URL of this page
https://metraipolis.com/documento/dc_36dd76b9541b
How to cite
Trust-But-Verify: Poisoning-Resilient Locally Private Graph Learning Protocols — arXiv:2609.07063 — arXiv (en), https://arxiv.org/abs/2609.07063 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_36dd76b9541b (Metraipolis archive dc_36dd76b9541b, sha256 ae12b8ed2076153c7de88d4cda3b3ba292e9a986a0fc0b0f22e532f0dd64d5ed)
BibTeX
@misc{dc36dd76b9541b,
title = {Trust-But-Verify: Poisoning-Resilient Locally Private Graph Learning Protocols — arXiv:2609.07063},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.07063},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_36dd76b9541b; sha256 ae12b8ed2076153c7de88d4cda3b3ba292e9a986a0fc0b0f22e532f0dd64d5ed},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07063. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Built upon local differential privacy (LDP), locally private graph learning protocols have emerged as an important paradigm for decentralized graph learning, balancing privacy protection and learning utility. Under such protocols, each user locally perturbs their node features and adjacency information before transmission, ensuring formal privacy guarantees without original data leaving the device. However, the inherently open participation nature renders these protocols critically vulnerable to data poisoning attacks, where adversaries inject carefully crafted malicious nodes to corrupt neighborhood aggregation and degrade downstream utility. Despite the severity of this threat, effective defenses in this setting remain largely unexplored. In this paper, we propose VERITAS, a poisoning-resilient locally private graph learning protocol built on a trust-but-verify paradigm. By introducing a verification list encoding graded peer trust levels, VERITAS jointly privatizes node features and graph structure on the user side, while exploiting bilateral attestation asymmetry on the server side to identify and prune malicious nodes. Concretely, VERITAS comprises four synergistic stages: (1) local data perturbation, (2) attestation-driven malicious node pruning, (3) utility restoration via dual denoising, and (4) robust private graph learning. Extensive experiments on four real-world benchmark datasets across multiple LDP mechanisms and GNN architectures demonstrate that VERITAS effectively defends against data poisoning attacks and significantly improves downstream graph learning utility under rigorous privacy guarantees. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.07063 — 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 2026-10-16T13:39:42.935Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).