PulseAugur
中
实时 08:34:54
English(EN) Stealing Exact Training Data from Other Clients during Federated Learning

新攻击可从联邦学习客户端恢复精确训练数据

研究人员开发了一种新颖的攻击流程,可以从参与联邦学习的客户端中提取精确的训练数据。该方法解决了先前梯度反演攻击的局限性,这些攻击在诸如FedAvg之类的算法中,由于客户端贡献的纠缠而难以恢复精确的文本数据。新的流程迭代地减去恢复的句子梯度,从而实现了100%精度的精确句子恢复,并在先前方法完全失败的挑战性场景中恢复了高达80.2%的客户端句子。 AI

影响 这项研究突显了联邦学习中重大的隐私风险,可能影响分布式AI训练的采用和安全协议。

排序理由 该集群包含一篇详细介绍新攻击方法的论文。[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 →

新攻击可从联邦学习客户端恢复精确训练数据

本文如何被排名

Signal score
21 / 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攻击方法的论文。[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]

  1. arXiv cs.LG TIER_1 English(EN) · Omkar Shrikanth, Soham Dambalkar, Parag Jyoti Pal, Advik Raj Basani, Arnab K. Paul ·

    联邦学习中窃取其他客户端的精确训练数据

    arXiv:2611.24689v1 Announce Type: new Abstract: Malicious adversaries can employ gradient inversion attacks to reverse-engineer private data using the model updates of a round in Federated Learning. While there have been developments in gradient inversion for text, exact text rec…