PulseAugur
中
实时 11:19:06
English(EN) Optimizing Byzantine Node Placement in Decentralized Federated Learning

联邦学习研究通过新算法和放置策略应对拜占庭攻击

作者 PulseAugur 编辑部 · [3 个来源] ·

研究人员正在探索提高联邦学习的安全性和效率，特别是针对拜占庭攻击，在这种攻击中，恶意参与者会破坏训练过程。一项研究引入了一种 Nesterov 加速联邦学习算法 (Byrd-NAFL)，该算法将动量与鲁棒聚合规则相结合，以确保快速安全的收敛，并在数值实验中展示了卓越的性能。另一篇论文侧重于优化去中心化联邦学习系统中拜占庭节点的放置，提出了一种拜占庭放置影响 (BPI) 指标来量化受损节点对诚实参与者的影响，并开发了识别破坏性配置的算法。 AI

影响 这些研究进展旨在使联邦学习更加安全和高效，可能使其在敏感应用中得到更广泛的应用。

排序理由 两篇在 arXiv 上发表的学术论文，详细介绍了改进联邦学习安全性和效率的新方法。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

联邦学习研究通过新算法和放置策略应对拜占庭攻击

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
两篇在 arXiv 上发表的学术论文，详细介绍了改进联邦学习安全性和效率的新方法。
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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
53 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准。

报道来源 [3]

  1. arXiv cs.LG TIER_1 English(EN) · Ming Xiang, Stratis Ioannidis, Edmund Yeh, Carlee Joe-Wong, Lili Su ·

    超越静态客户端不可用性的韧性：解锁高效且无偏的联邦学习

    arXiv:2609.04763v1 Announce Type: new Abstract: Due to resource constraints or external and internal uncertainties, clients in real-world federated learning systems are often intermittently available edge devices. In highly dynamic environments, the parameter server lacks prior r…

  2. arXiv cs.LG TIER_1 English(EN) · Lihan Xu, Xiaoyi Fan, Gang Wang, Runhao Zeng, Xiping Hu, Yanjie Dong ·

    一种Nesterov加速的拜占庭鲁棒联邦学习

    arXiv:2511.02657v2 Announce Type: replace Abstract: We investigate robust federated learning, where a group of workers collaboratively train a shared model under the orchestration of a central server in the presence of Byzantine adversaries capable of arbitrary and potentially ma…

  3. arXiv cs.AI TIER_1 English(EN) · Edoardo Gabrielli, Gabriele Tolomei ·

    优化去中心化联邦学习中的拜占庭节点放置

    arXiv:2609.01495v1 Announce Type: cross Abstract: Security evaluations of decentralized federated learning (DFL) typically focus on how Byzantine participants behave, while largely overlooking which participants are compromised. Yet, because aggregation is distributed over a comm…

相关实体

相关话题