English(EN) Shift-aware score transport for privacy auditing without retraining

新方法改进了机器学习模型的隐私审计，即使在数据分布发生变化的情况下

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-23 04:00

研究人员开发了一种名为“移位感知评分传输”的新方法，以提高机器学习模型隐私审计的准确性。该技术解决了分布移位带来的挑战，即审计使用的数据与模型的训练数据不同，导致隐私评估出现偏差。通过学习分布外非成员数据表示与隐私分数之间的关系，该方法可以将这些见解迁移到目标分布并纠正审计错误。与现有方法相比，这种方法在无法进行模型重新训练的观察性审计环境中，可以产生更稳定的隐私估计和更紧密的下界。 AI

影响提高了已部署人工智能模型隐私评估的可靠性，尤其是在无法重新训练的情况下。

排序理由该集群包含一篇详细介绍机器学习隐私审计新方法的论文。[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: 4 / 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隐私审计新方法的论文。[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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Yaohong Yang, Gauri Pradhan, Qi Chen, Samuel Kaski, Antti Honkela · 2026-10-23 04:00

Shift-aware score transport for privacy auditing without retraining

arXiv:2610.31549v1 Announce Type: new Abstract: Privacy auditing empirically assesses privacy leakage by using membership inference attacks to establish lower bounds on privacy loss. We consider an observational auditing setting in which the auditor cannot insert canaries, contro…

本文如何被排名

报道来源 [1]

Shift-aware score transport for privacy auditing without retraining

相关实体

相关话题