English(EN) How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces

研究发现：大型语言模型工具调用追踪带来重大隐私风险

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-02 05:00

一项发表在arXiv上的新研究探讨了与外部工具交互的大型语言模型（LLM）代理相关的隐私风险。研究人员推出了PrivacyTrace，这是一个基准数据集，旨在评估如何从模型上下文协议（MCP）等协议生成的工具调用追踪中推断用户画像。实验表明，这些追踪可以将用户属性推断的成功率提高到26.25%，显著高于以往的方法。研究强调，工具参数和返回结果是造成这种隐私泄露的关键来源，而跨会话追踪链接则进一步加剧了风险，凸显了在代理-工具交互中采用隐私保护机制的必要性。 AI

影响强调了大型语言模型代理交互中潜在的隐私漏洞，需要开发隐私保护机制。

排序理由该集群包含一篇研究论文，详细介绍了新的基准和关于大型语言模型工具调用追踪隐私泄露的发现。[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: 1 / 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，详细介绍了新的基准和关于大型语言模型工具调用追踪隐私泄露的发现。[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: 1 days old; Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Donghang Duan, Qingyu Liu, Yifei Liu, Na Zou, Xia Hu, Dongrui Liu · 2026-11-02 05:00

How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces

arXiv:2610.41885v1 Announce Type: cross Abstract: Large language model (LLM)-based agents interact with external tools through protocols such as the Model Context Protocol (MCP), producing tool-call traces that may expose behavioral signals about users. In this work, we systemati…

本文如何被排名

报道来源 [1]

How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces

相关实体

相关话题