AI Sandboxes: A Threat Model, Taxonomy, and Measurement Framework

2026-06-16

AI Summary

This work addresses the current lack of a systematic understanding of the capabilities of AI sandboxes in ensuring safety, security, and regulatory compliance, particularly within physical AI and cyber-physical systems. It proposes the first unified, assurance-oriented framework for AI sandboxes, introducing a formal boundary definition, a comprehensive sandbox taxonomy, a threat model targeting the assurance mechanisms themselves, and a quantifiable evaluation methodology spanning six dimensions—including fidelity and controllability. Through formal modeling, threat analysis, and multi-case validation, the study clarifies what aspects of AI behavior can be effectively tested in sandboxes, which risk categories can be meaningfully controlled, and what forms of evidence such environments can generate to support safety and compliance claims, thereby establishing foundational tools for trustworthy AI verification.

Abstract

AI systems are increasingly evaluated in bounded environments that combine isolation, simulation, instrumentation, supervision, and evidence capture. For physical AI, AIoT, and cyber-physical systems, this shift is not a matter of terminology: the system under test may sense, decide, actuate, communicate, and fail through physical processes, networked devices, and human operators. This article develops an assurance-oriented account of AI sandboxes as controlled environments for testing, evaluation, verification, and validation across digital AI, embodied autonomy, and cyber-physical deployments. We formalize the sandbox boundary and a weakest-link rule for composing per-dimension evidence into a bounded deployment claim; separate major sandbox archetypes; define a cyber-physical threat model that includes attacks on the assurance apparatus itself; and introduce a measurement framework spanning fidelity, controllability, observability, containment, reproducibility, and governance artifacts, instantiated on three worked case studies of real sandboxes. The resulting threat model, taxonomy, and measurement framework clarify what a sandbox can validly test, which risks it can contain, and what forms of evidence it can support for safety, security, and regulatory assurance.

Problem

• AI sandbox
• cyber-physical systems
• threat model
• assurance
• evaluation framework

Innovation

• AI sandbox
• cyber-physical threat model
• assurance framework
• measurement framework
• embodied autonomy