English(EN) GraphProfiler: Source-Linked Sensitive Attribute Inference via Personal Knowledge Graphs

新的GraphProfiler工具可将LLM推断追溯到特定用户帖子

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-14 04:00

研究人员开发了GraphProfiler，一个新颖的可审计的基于LLM的系统，旨在从在线内容中推断敏感用户属性。与以前的方法不同，GraphProfiler构建了一个源链接的个人知识图谱，使其能够将推断追溯到特定的帖子和引用的证据。这种方法旨在通过识别导致属性泄露的确切内容来增强隐私缓解。该系统在SynthPAI基准测试上达到了86.7%的攻击成功率，在PANDORA上达到了84.6%，同时为其98%以上的预测提供了支持证据。 AI

影响通过识别泄露敏感用户信息的特定内容，实现更有针对性的隐私缓解。

排序理由该项目是一篇研究论文，详细介绍了一种使用LLM和知识图谱进行敏感属性推断的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 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: 26 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该项目是一篇研究论文，详细介绍了一种使用LLM和知识图谱进行敏感属性推断的新方法。[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: 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.CL TIER_1 English(EN) · Ahmed Sohair Khan, Estrid He, Chenglong Ma, Monica Wachowicz, Elham Naghizade · 2026-09-14 04:00

GraphProfiler：通过个人知识图谱进行源链接敏感属性推断

arXiv:2609.12448v1 Announce Type: new Abstract: Sensitive attributes such as age, income, and occupation can be inferred from user-generated content by aggregating indirect cues across many ordinary posts. LLM-based profilers can perform this aggregation automatically and with hi…

本文如何被排名

报道来源 [1]

GraphProfiler：通过个人知识图谱进行源链接敏感属性推断

相关实体

相关话题