English(EN) When Agents Control Robots: A Zero Trust Policy Model for Agentic Cyber-Physical Systems

新的零信任策略模型保护AI控制的机器人

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-25 10:00

一篇新论文介绍了一种名为ZTPM的零信任策略模型，该模型旨在保护控制工业机器人的大型基础模型（LFM）驱动的系统。该模型利用五个执行域中的25个类型化原语，解决了在代理式网络物理系统中识别出的五类特定攻击。实证评估表明，执行参数选择是模型依赖且非确定性的，这凸显了在物理执行边界进行策略级别强制执行的必要性。 AI

影响这项研究为AI控制的物理系统引入了一个安全框架，这对于工业自动化和机器人安全至关重要。

排序理由该集群包含一篇详细介绍新模型和实证评估的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.MA (Multiagent) 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: 0 / 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新模型和实证评估的学术论文。[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: 116 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.MA (Multiagent) TIER_1 English(EN) · Susan Rea · 2026-05-25 10:00

当智能体控制机器人：面向智能体网络物理系统的零信任策略模型

Multi-agent systems powered by large foundation models (LFMs) are increasingly deployed to control industrial robots through natural language, creating deployments in which security failures produce physical consequences. We analyse this threat landscape through Cobot-Claw, a dep…

本文如何被排名

报道来源 [1]

当智能体控制机器人：面向智能体网络物理系统的零信任策略模型

相关实体

相关话题