PulseAugur
实时 10:12:38
English(EN) LoMime: Query-Efficient Membership Inference using Model Extraction in Label-Only Settings

新的LoMime方法实现了对ML模型的有效隐私攻击

研究人员开发了一种名为LoMime的新方法,用于对机器学习模型执行成员推理攻击(MIA),即使在仅有标签访问的情况下也是如此。该方法利用模型提取,即训练一个代理模型来模仿目标模型的行为。通过使用主动采样和合成数据,LoMime显著降低了通常与仅标签MIA相关的查询成本,以一小部分查询实现了与最先进方法相当的准确性。该框架已在表格数据集上证明了有效性,并有望扩展到用于图像识别的深度神经网络。 AI

影响 引入了一种更有效的ML模型隐私攻击方法,可能影响未来的防御策略。

排序理由 详细介绍成员推理攻击新方法的学术论文。[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 →

新的LoMime方法实现了对ML模型的有效隐私攻击

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
Tool
详细介绍成员推理攻击新方法的学术论文。[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
79 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]

  1. arXiv cs.LG TIER_1 English(EN) · Abdullah Caglar Oksuz, Anisa Halimi, Erman Ayday ·

    LoMime:在仅标签设置中使用模型提取进行查询高效成员推理

    arXiv:2602.18934v2 Announce Type: replace Abstract: Membership inference attacks (MIAs) threaten the privacy of machine learning models by revealing whether a specific data point was used during training. Existing MIAs often rely on impractical assumptions, such as access to publ…