English(EN) ActionGuard: Tool Call Authorization under Poisoned Skills

ActionGuard系统可防止LLM代理中的恶意工具调用

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-01 04:00

一项新的研究论文介绍ActionGuard，一个旨在防止由LLM代理中的受损第三方技能发起的恶意工具调用的系统。ActionGuard通过在执行前检查工具调用，将代理的动作生成上下文与安全防护的授权上下文分离开来运行。它使用平衡的技能配置文件和运行时证据来确定动作是否由用户的请求所证明。评估表明，ActionGuard在保持高良性任务完成率的同时，显著降低了攻击成功率。 AI

影响通过防止受损技能触发的未经授权的操作来增强LLM代理的安全性。

排序理由该集群包含一篇详细介绍LLM安全新系统的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 22 / 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LLM安全新系统的研究论文。[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.AI TIER_1 English(EN) · Jihun Han, Yejin Jang, Byung Il Kwak, Mee Lan Han · 2026-10-01 04:00

ActionGuard：受毒害技能下的工具调用授权

arXiv:2609.39450v1 Announce Type: cross Abstract: LLM-based agents extend their capabilities through third-party skills that provide task-specific instructions, scripts, and tool-use procedures. However, malicious instructions inserted into an otherwise benign skill can cause a b…

本文如何被排名

报道来源 [1]

ActionGuard：受毒害技能下的工具调用授权

相关实体

相关话题