网安资讯详情 - SecLens 情报雷达

网安资讯,一网打尽。汇集权威漏洞通告与行业要闻,结合分组浏览、智能过滤、RSS订阅 和 Webhook 推送,多通道拓展您的安全情报视野。

Ghost Tool Calls: Issue-Time Privacy for Speculative Agent Tools

来源: arxiv_cs_cr · 发布时间 2026-06-02 00:53 (UTC+08:00) · 抓取时间 2026-06-02 19:10 (UTC+08:00)

原文链接

摘要

Tool-augmented language agents speculatively issue likely future tool calls to hide latency, but those calls leak inferred user intent to external services before the agent commits to the branch. Every external observer that received the call retains the disclosure after the agent abandons the branch. Timing is the issue, not authorization: no commit-time cleanup, read-only restriction, or access-control allow-list unsends what an observer already holds. We call these invocations ghost tool calls and propose Speculative Tool Privacy Contracts, a runtime abstraction that treats observation before commitment as a first-class effect, distinct from state mutation. We implement the contracts in a prototype runtime and evaluate twelve policies across three corpora. Speculative dispatch increases what an observer can infer about user intent; post-hoc filters, read-only restrictions, and access-control allow-lists leave that inference intact; only issue-time policies that change or suppress the speculative call's argument or destination projection before dispatch reduce it.

正文

Tool-augmented language agents speculatively issue likely future tool calls to hide latency, but those calls leak inferred user intent to external services before the agent commits to the branch. Every external observer that received the call retains the disclosure after the agent abandons the branch. Timing is the issue, not authorization: no commit-time cleanup, read-only restriction, or access-control allow-list unsends what an observer already holds. We call these invocations ghost tool calls and propose Speculative Tool Privacy Contracts, a runtime abstraction that treats observation before commitment as a first-class effect, distinct from state mutation. We implement the contracts in a prototype runtime and evaluate twelve policies across three corpora. Speculative dispatch increases what an observer can infer about user intent; post-hoc filters, read-only restrictions, and access-control allow-lists leave that inference intact; only issue-time policies that change or suppress the speculative call's argument or destination projection before dispatch reduce it. Authors: Bardia Mohammadi, Lars Klein, Akhil Arora, Laurent Bindschaedler Categories: cs.CR, cs.AI, cs.CL PDF: https://arxiv.org/pdf/2606.02483v1

标签

扩展字段

{
  "arxiv_id": "2606.02483v1",
  "authors": [
    "Bardia Mohammadi",
    "Lars Klein",
    "Akhil Arora",
    "Laurent Bindschaedler"
  ],
  "categories": [
    "cs.CR",
    "cs.AI",
    "cs.CL"
  ],
  "comment": null,
  "doi": null,
  "entry_id": "https://arxiv.org/abs/2606.02483v1",
  "pdf_url": "https://arxiv.org/pdf/2606.02483v1",
  "primary_category": "cs.CR",
  "search_query": "cat:cs.CR",
  "updated_at": "2026-06-01T16:53:19+00:00"
}