English(EN) Efficient Unlearning with Privacy Guarantees

新的EUPG框架提供高效、私密的机器学习遗忘

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-30 04:00

一种名为EUPG的新型机器学习遗忘框架已被开发出来，能够高效地从机器学习模型中移除个人数据，同时保持隐私保障。该方法涉及使用诸如k-匿名和ε-差分隐私等隐私保护技术对模型进行预训练。实证评估表明，EUPG在效用和遗忘效果方面可与精确遗忘方法相媲美，但计算和存储成本却显著降低。 AI

影响通过提供高效且有保障的方法来从机器学习模型中移除个人数据，从而实现对数据隐私法规的合规。

排序理由该集群包含一篇详细介绍机器学习遗忘新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

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; 该集群包含一篇详细介绍机器学习遗忘新方法的学术论文。[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: 100 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。

arXiv cs.LG TIER_1 English(EN) · Josep Domingo-Ferrer, Najeeb Jebreel, David S\'anchez · 2026-06-30 04:00

高效的带隐私保障的遗忘

arXiv:2507.04771v2 Announce Type: replace-cross Abstract: Privacy protection laws, such as the GDPR, grant individuals the right to request the forgetting of their personal data not only from databases but also from machine learning (ML) models trained on them. Machine unlearning…