新的梯度反演攻击揭示了联邦学习中重大的隐私风险

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-11 04:00

研究人员开发了一种受LT码启发的联邦学习梯度反演攻击新方法。该技术允许从单轮FedSGD中精确恢复训练数据和标签，性能显著优于之前的单轮攻击。即使是被动攻击者也能从ImageNet等基准测试中恢复高比例的批次，这表明联邦学习中的隐私风险被低估了。 AI

影响这项研究突显了联邦学习中重大的隐私漏洞，可能会影响分布式AI系统中数据的共享和安全方式。

排序理由该集群包含一篇研究论文，详细介绍了联邦学习中梯度反演攻击的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

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: 15 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇研究论文，详细介绍了联邦学习中梯度反演攻击的新方法。[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。

arXiv cs.AI TIER_1 English(EN) · Saeed Shariati, Mohsen Alambardar Meybodi · 2026-09-11 04:00

基于LT码启发式剥离的联邦学习级联梯度反演

arXiv:2609.09659v1 Announce Type: cross Abstract: Federated learning shares model updates rather than raw data, yet these updates can be inverted to reconstruct the clients' training data. Analytic reconstruction attacks, which invert a gradient in closed form, degrade as the bat…