English(EN) Approaching the Harm of Gradient Attacks While Only Flipping Labels

新研究详细介绍了分布式机器学习系统的标签翻转攻击

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-10 04:00

一篇新的研究论文探讨了分布式机器学习系统中梯度攻击的潜在危害，特别是关注标签翻转。该研究将这些攻击形式化为一个约束优化问题，并推导出一个贪婪的标签选择规则，该规则在均值聚合下对攻击者来说是可证明最优的。在实践中，研究表明优化的标签翻转可以显著降低模型准确性，甚至可以转移到其他聚合方法，如中位数和截尾均值，从而构成重大的可用性威胁。 AI

影响突显了分布式机器学习系统中的一个重大安全漏洞，可能影响联邦学习部署的鲁棒性。

排序理由关于机器学习安全的学术论文。[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 →

本文如何被排名

Signal score: 12 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 关于机器学习安全的学术论文。[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]

arXiv cs.LG TIER_1 English(EN) · Abdessamad El-Kabid, El-Mahdi El-Mhamdi · 2026-09-10 04:00

仅通过翻转标签即可逼近梯度攻击的危害

arXiv:2503.00140v3 Announce Type: replace-cross Abstract: Machine learning systems deployed in distributed or federated environments are highly susceptible to adversarial manipulations, particularly availability attacks -- rendering the trained model unavailable. Prior research i…

本文如何被排名

报道来源 [1]

仅通过翻转标签即可逼近梯度攻击的危害

相关实体

相关话题