English(EN) Federated Art Chase: Privacy Leakage and Data Poisoning in Federated Fine-Tuning

联邦学习易受隐私泄露和数据投毒攻击

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-16 04:00

一份新报告详细介绍了联邦学习的漏洞，这是一种将预训练模型适配到本地用户数据的方法。研究人员发现，中央服务器可以从单个客户端更新中恢复私有标签集，尽管重建可能缺乏细节。虽然标签计数恢复随着客户端数量的增加而减少，但后门攻击仍然是一个重大威胁，随着恶意客户端数量的增加，成功率也会增加。FLTrust 等防御机制可以缓解这些风险，但在所有客户端都受到损害时则无效。 AI

影响凸显了联邦学习中关键的安全和隐私风险，需要强大的防御机制才能广泛采用。

排序理由研究论文，详细介绍了联邦学习中的漏洞。[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: 14 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 研究论文，详细介绍了联邦学习中的漏洞。[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; 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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Vasileios Perifanis, Nikolaos Pavlidis · 2026-10-16 04:00

联邦艺术追逐：联邦微调中的隐私泄露与数据投毒

arXiv:2610.21547v1 Announce Type: new Abstract: Federated learning (FL) is increasingly used to adapt a pretrained, centrally fine-tuned model to data that remain on user devices, beyond training a model from scratch. In this report, prepared for the 4th Federated Machine Learnin…

本文如何被排名

报道来源 [1]

联邦艺术追逐：联邦微调中的隐私泄露与数据投毒

相关实体

相关话题