English(EN) Peer-Relative Trust-Guided Update Screening for Robust Semi-Decentralized Federated Learning under Label-Flipping Attacks

新的SDFL方法提高了对标签翻转攻击的鲁棒性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-19 03:04

研究人员开发了一种新的半分布式联邦学习（SDFL）方法，旨在提高对标签翻转攻击的鲁棒性。该方法在最近的一篇arXiv论文中有所介绍，它结合了鲁棒的验证效用分数以及基于方向和范数的更新质量来筛选恶意客户端的更新。在MNIST数据集上，使用50个客户端和20%的持久标签翻转攻击者进行的评估表明，即使在数据异质性中度到严重的情况下，也具有高准确率和对恶意提交的有效拒绝。 AI

影响增强了分布式人工智能训练场景中的安全性和鲁棒性。

排序理由学术论文，详细介绍了一种新的联邦学习方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.NE (Neural & Evolutionary) 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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了一种新的联邦学习方法。[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: 6 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.NE (Neural & Evolutionary) TIER_1 English(EN) · Sandhya Joshi · 2026-10-19 03:04

面向标签翻转攻击下鲁棒半分布式联邦学习的同伴相对信任引导更新筛选

Trust and reputation mechanisms can reduce the influence of malicious clients in federated learning (FL), but strict update filtering is difficult under non-independent and identically distributed (non-IID) data because honest local updates may temporarily reduce performance on a…

本文如何被排名

报道来源 [1]

面向标签翻转攻击下鲁棒半分布式联邦学习的同伴相对信任引导更新筛选

相关实体

相关话题