English(EN) Data-Poisoning Audits for Causal Effect Estimation

新的审计框架可检测因果效应估计中的数据投毒

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-23 04:00

已开发出一种用于观察性研究中因果效应估计的新型数据投毒审计框架。该框架允许分析人员指定可行记录、附加预算和来源容量，使对手能够战略性地选择记录来改变报告的治疗效果。所提出的方法包括用于精确最坏情况移动的贪婪扫描和用于考虑干扰重拟的总体影响分数，为因果报告和保障措施的设计提供了更可靠的方法。 AI

影响通过提供检测和减轻数据操纵的工具，增强了 AI 模型中因果推理的可靠性。

排序理由该集群包含一篇研究论文，详细介绍了因果效应估计中数据投毒审计的新方法。[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; 该集群包含一篇研究论文，详细介绍了因果效应估计中数据投毒审计的新方法。[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: 60 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 stat.ML TIER_1 English(EN) · Kwangho Kim · 2026-07-23 04:00

用于因果效应估计的数据投毒审计

arXiv:2607.19692v1 Announce Type: new Abstract: Observational causal analyses increasingly pool records across sites, vendors, and collection systems, creating vulnerability to append-only attacks in which plausible records are strategically selected to alter a reported treatment…