English(EN) Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuning

新的PromptMIA攻击针对联邦提示调优中的隐私

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-05 05:00

研究人员开发了一种名为PromptMIA的新隐私攻击，专门用于联邦提示调优场景。该攻击利用恶意服务器在协作训练期间引入的对抗性构造的提示，来推断目标数据点是否属于某个客户端的私有数据集。PromptMIA的性能显著优于现有的联邦成员推断攻击，并表明当前防御措施通常无效，突显了在联邦提示调优中需要专门的隐私机制。 AI

影响强调了联邦学习中的一种新的隐私漏洞，有必要开发专门针对提示调优的防御措施。

排序理由该集群包含一篇详细介绍新型隐私攻击方法的学术论文。[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: 26 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍新型隐私攻击方法的学术论文。[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; 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) · Quan Minh Nguyen, Min-Seon Kim, Hoang M. Ngo, Trong Nghia Hoang, Hyuk-Yoon Kwon, My T. Thai · 2026-11-05 05:00

利用软提示进行联邦提示调优中的隐私攻击

arXiv:2601.06641v4 Announce Type: replace Abstract: Membership inference attacks (MIAs) pose a serious privacy threat in federated learning (FL). While MIAs have been extensively studied in standard FL, the recent shift toward federated fine-tuning introduces new and largely unex…

本文如何被排名

报道来源 [1]

利用软提示进行联邦提示调优中的隐私攻击

相关实体

相关话题