When Agents Control Robots: A Zero Trust Policy Model for Agentic Cyber-Physical Systems
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911715673767936 |
|---|---|
| author | Ranathunga, Tharindu Fernando, Kavishka Rea, Susan |
| author_facet | Ranathunga, Tharindu Fernando, Kavishka Rea, Susan |
| contents | 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 deployed four-agent system for UR3e robotic arm control, and identify five attack classes specific to agentic cyber-physical systems. We propose ZTPM, a Zero Trust Policy Model comprising 25 typed primitives across five enforcement domains with Physical Impact Tiers as a runtime policy dimension. An empirical evaluation across 60 execution traces on two LFM backends provides initial evidence that actuation parameter selection is model-dependent and non-deterministic, motivating the need for policy-level enforcement at the physical actuation boundary. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_25653 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | When Agents Control Robots: A Zero Trust Policy Model for Agentic Cyber-Physical Systems Ranathunga, Tharindu Fernando, Kavishka Rea, Susan Distributed, Parallel, and Cluster Computing Multiagent Systems 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 deployed four-agent system for UR3e robotic arm control, and identify five attack classes specific to agentic cyber-physical systems. We propose ZTPM, a Zero Trust Policy Model comprising 25 typed primitives across five enforcement domains with Physical Impact Tiers as a runtime policy dimension. An empirical evaluation across 60 execution traces on two LFM backends provides initial evidence that actuation parameter selection is model-dependent and non-deterministic, motivating the need for policy-level enforcement at the physical actuation boundary. |
| title | When Agents Control Robots: A Zero Trust Policy Model for Agentic Cyber-Physical Systems |
| topic | Distributed, Parallel, and Cluster Computing Multiagent Systems |
| url | https://arxiv.org/abs/2605.25653 |