AI Sandboxes: A Threat Model, Taxonomy, and Measurement Framework
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Quantifying Frontier LLM Capabilities for Container Sandbox Escape
Large language models (LLMs) increasingly act as autonomous agents, using tools to execute code, read and write files, and access networks, creating novel security risks. To mitigate these risks, agents are commonly depl…
AI Code Sandboxes: A Comparative Security Study. Part 1 of 2 -- Engine-Level Properties (Attack Surface, Leakage, Stackability, CVE History, Patch Cadence, Fuzzing)
This paper reads six engine-level measurements together -- 1.1 host attack surface, 1.2 information leakage, 1.3 defense-in-depth stackability, 1.4 public CVE history, 1.5 patch cadence, and 1.6 upstream fuzzing posture …
Mapping the Exploitation Surface: A 10,000-Trial Taxonomy of What Makes LLM Agents Exploit Vulnerabilities
LLM agents with tool access can discover and exploit security vulnerabilities. This is known. What is not known is which features of a system prompt trigger this behaviour, and which do not. We present a systematic taxon…
MCP-38: A Comprehensive Threat Taxonomy for Model Context Protocol Systems (v1.0)
The Model Context Protocol (MCP) introduces a structurally distinct attack surface that existing threat frameworks, designed for traditional software systems or generic LLM deployments, do not adequately cover. This pape…
Operationalising AI Regulatory Sandboxes under the EU AI Act: The Triple Challenge of Capacity, Coordination and Attractiveness to Providers
The EU AI Act provides a rulebook for all AI systems being put on the market or into service in the European Union. This article investigates the requirement under the AI Act that Member States establish national AI regu…