跳到正文

Network-Exposed Configuration Attacks on LLM-Controlled Social Robots

机器人 0 次浏览

原文:Network-Exposed Configuration Attacks on LLM-Controlled Social Robots

作者:Stanley Akingbola, Ugbede Ibrahim, Yan Lin Aung, Quang Dan Le, Hong Qing Yu

来源:arXiv cs.RO(机器人)

正文

Computer Science > Cryptography and Security

arXiv:2611.22761v1 (cs)

[Submitted on 17 Nov 2026]

Title:Network-Exposed Configuration Attacks on LLM-Controlled Social Robots

Authors:Stanley Akingbola, Ugbede Ibrahim, Yan Lin Aung, Quang Dan Le, Hong Qing Yu

View a PDF of the paper titled Network-Exposed Configuration Attacks on LLM-Controlled Social Robots, by Stanley Akingbola and 4 other authors

View PDF

HTML (experimental)

Abstract:Large language models (LLMs) in embodied robots create security dependencies beyond inference. We investigate a network-exposed configuration attack on the Pollen Robotics Reachy Mini Lite, allowing an unauthenticated attacker to replace personality settings and the cloud LLM’s system prompt through a management interface, without adversarial conversational input. Eleven prompt-injection attempts across five categories were reported as resisted, whereas both configuration-layer attack paths produced observable behavioural changes on physical hardware. We demonstrate local and network-adjacent access, mapping the weakness to CWE-306 (Missing Authentication for a Critical Function) and CWE-1327 (Binding to an Unrestricted IP Address), with a reported CVSS v3.1 score of 6.5 (Medium). A configuration endpoint also accepts cross-origin requests without a CORS preflight (CWE-352; 6.5 Medium), while the persistent-memory sink stores content without enforcing its stated restrictions. A source review of 59 public repositories identifies missing authentication in 10 of 11 source-verifiable genuine applications, or 11 of 11 including a framework-default case. These findings indicate recurrence within the sampled repositories, not prevalence in commercial products. We characterise a deployment gap between developer-oriented network assumptions and consumer-facing embodied AI security: inference-layer refusal cannot prevent unauthorised changes to model instructions. Potential consequences include surveillance through onboard cameras and microphones and social engineering of nearby users. Proof-of-concept code, evidence and the survey are available at this https URL.

Subjects:

Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Robotics (cs.RO)

Cite as:

arXiv:2611.22761 [cs.CR]

(or

arXiv:2611.22761v1 [cs.CR] for this version)

https://doi.org/10.48550/arXiv.2611.22761

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

主题

安全 · 人工智能 · 机器人


由「前沿雷达」于 2026-11-17 采集。正文取自原文页面,已保留出处链接。标题与正文版权归原作者所有。

评论

加载中…