PulseAugur
中
实时 13:36:54
English(EN) A Path Integral Surrogate for Multi-Step Gradient Inversion in Federated Learning

新的PI-SME方法增强了联邦学习中的梯度反演攻击

研究人员开发了一种名为路径积分代理模型扩展(PI-SME)的新方法,以改进联邦学习中的梯度反演攻击。该技术将客户端的模型更新视为梯度场的路径积分,并使用沿可学习贝塞尔曲线的高斯-勒让德求积法进行近似。PI-SME旨在通过分析客户端初始和最终模型状态之间轨迹上的多个点,比现有方法更准确地重建私有输入数据。在CIFAR-100和FEMNIST数据集上的实验表明,PI-SME在各种条件下都能有效地忠实重建私有输入。 AI

影响 这项研究突显了联邦学习中潜在的隐私漏洞,促使进一步研究鲁棒的防御机制。

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]

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 →

新的PI-SME方法增强了联邦学习中的梯度反演攻击

本文如何被排名

Signal score
7 / 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
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]

  1. arXiv cs.LG TIER_1 English(EN) · Agnivo Ghosh, Saumik Bhattacharya ·

    联邦学习中多步梯度反演的路径积分代理

    arXiv:2610.03597v1 Announce Type: new Abstract: Federated learning lets many clients train a shared model together without ever sending their private data to a central server. Each client shares only a model update, and this update should reveal far less about the client than its…