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

新攻击可推断数据何时用于持续模型训练

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-04 00:36

研究人员引入了一种名为 TMIA 的新方法，用于检测特定数据样本何时被用于持续更新的机器学习模型的训练中。这种时间成员推断攻击利用双向 LSTM，可以推断出样本在训练数据中包含的时间或时间间隔。在各种语言和图像分类模型上的实验证明了 TMIA 的有效性，显著优于现有方法。该研究还探讨了潜在的防御措施，并强调了时间隐私和模型效用之间固有的权衡。 AI

影响这项研究突显了持续更新模型中新的时间隐私风险，可能影响数据的管理方式和模型的安全性。

排序理由这是一篇详细介绍机器学习模型新攻击方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 Hugging Face Daily Papers 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; 这是一篇详细介绍机器学习模型新攻击方法的学术论文。[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: 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]

Hugging Face Daily Papers TIER_1 English(EN) · 2026-11-04 00:36

时机至关重要：在持续更新的模型中推断时间成员资格

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 present the first systematic study of temporal pri…

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