Trust Mechanisms for Offline Generative AI at the Edge: A Connectivity-Regime Framework and an Empirical Study on a Raspberry Pi 5

A proposed connectivity-regime framework spanning five levels, C0 through C4, classifies inference-time trust mechanisms for generative AI and large language models deployed on IoT devices where connectivity is intermittent, restricted or absent, and the work includes an empirical study run on a Raspberry Pi 5. The framework addresses the gap that most generative AI deployments assume cloud connectivity, an assumption the authors state does not hold in many IoT settings.

Generative AI and large language models LLMs are moving into the Internet of Things, yet most deployments assume cloud connectivity, and many IoT settings have intermittent, restricted, or no connectivity. We propose a connectivity-regime framework C0-C4 , a taxonomy of inference-time trust mecha