English(EN) HE-OFT: Privacy-Preserving One-Shot Federated Fine-Tuning under Homomorphic Encryption

新的HE-OFT协议支持隐私保护的联邦大语言模型微调

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-08 04:00

研究人员开发了HE-OFT，一种用于隐私保护的联邦大语言模型微调的新型协议。该方法允许多个参与方协作微调模型，而任何参与方都不会获得完全训练好的模型，从而解决了与受监管或专有资产相关的隐私问题。HE-OFT通过让客户端仅微调低秩适配器和分类器头，上传使用多方CKKS加密组合的加密贡献，而无需服务器解密来实现这一点。该协议表现出强大的性能，保持了公开模型85-96%的准确率，同时显著减少了数据传输需求。 AI

影响这项研究可能促进更安全的协作式人工智能开发，尤其是在模型隐私至关重要的受监管行业。

排序理由该集群描述了一篇详细介绍联邦学习新协议的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 8 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇详细介绍联邦学习新协议的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Halil \.Ibrahim Kanpak, Sinem Sav, Alptekin K\"up\c{c}\"u · 2026-10-08 04:00

HE-OFT：同态加密下的隐私保护单次联邦微调

arXiv:2610.08255v1 Announce Type: cross Abstract: Many organizations adapt large pretrained models to their own tasks by fine-tuning on private data. Several of these parties often hold data for the same task and wish to fine-tune a model together without pooling that data. Feder…

本文如何被排名

报道来源 [1]

HE-OFT：同态加密下的隐私保护单次联邦微调

相关实体

相关话题