English(EN) Timing is Everything: Inferring Temporal Membership in Continually Updated Models

新攻击推断持续更新的AI模型中的时间数据成员资格

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-05 05:00

研究人员推出了一种新颖的黑盒攻击TMIA，旨在推断持续更新的深度学习模型中的时间成员资格。该攻击旨在确定特定数据样本是否以及何时在模型训练中使用，并在时间戳和时间间隔级别上运行。TMIA利用双向LSTM分析模型在连续更新中的输出，在语言和图像分类模型的实验中显示出比现有方法显著的有效性。该研究还探讨了潜在的防御措施，并强调了隐私和模型效用之间的固有权衡。 AI

影响这项研究突显了持续更新的AI模型中一种新的隐私风险，可能影响未来的开发和防御策略。

排序理由该集群包含一篇学术论文，详细介绍了一种推断机器学习模型中时间成员资格的新方法。[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 →

本文如何被排名

Signal score: 26 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇学术论文，详细介绍了一种推断机器学习模型中时间成员资格的新方法。[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。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Jie Fu, Xiangpeng Deng, Yuan Hong, Wendy Hui Wang · 2026-11-05 05:00

时机至关重要：在持续更新的模型中推断时间成员资格

arXiv:2611.05781v1 Announce Type: cross Abstract: Continual model updating has become a common practice in the deployment of machine learning systems. However, the dynamic training behaviors give rise to new risks not sufficiently addressed by existing studies. In this paper, we …

本文如何被排名

报道来源 [1]

时机至关重要：在持续更新的模型中推断时间成员资格

相关实体

相关话题