English(EN) SoK: Privacy Attacks on Machine Learning via Explainable AI

可解释人工智能为机器学习模型创造了新的攻击面

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-11 04:00

一篇新发表在arXiv上的论文探讨了可解释人工智能（XAI）技术如何无意中为机器学习模型带来漏洞。该研究系统地梳理了25项利用解释进行攻击的研究，包括模型提取、成员推理和模型反演。它将对手获取解释信号的五种不同途径进行了分类，并强调风险取决于暴露的具体信号、获取方法、目标资产以及攻击者的现有知识。该论文主张对解释隐私进行端到端的评估，并根据获取途径和受保护资产量身定制防御措施。 AI

影响强调了由于可解释性功能而导致的机器学习模型的潜在隐私风险，并提出了对更强大防御措施的需求。

排序理由该集群包含一篇详细介绍机器学习模型隐私攻击的研究论文。[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: 15 / 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模型隐私攻击的研究论文。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Abdullah Caglar Oksuz, Anisa Halimi, Erman Ayday · 2026-09-11 04:00

SoK：通过可解释人工智能对机器学习的隐私攻击

arXiv:2609.10627v1 Announce Type: cross Abstract: Machine learning explanations reveal model behavior beyond predictions, creating attack surfaces for model confidentiality and data privacy. We systematize 25 studies that exploit explanations for model extraction, membership infe…

本文如何被排名

报道来源 [1]

SoK：通过可解释人工智能对机器学习的隐私攻击

相关实体

相关话题