Trust, but Validate the Instrument: Auditing AI-Generated RTL Verification Plans on Authored Security-Regression Proxies

2026-09-17

AI Summary

本文提出SecTB-RTL框架，通过31项任务和124个硬件安全回归测试，审计AI生成的RTL验证计划的有效性，发现仅满足提供者模式并不保证执行有效性。

Abstract

AI-generated RTL verification plans can satisfy a provider schema yet fail at the boundary to trusted execution. We present SecTB-RTL, an auditable framework covering 31 tasks and 124 authored hardware-security regressions. A deterministic non-AI baseline killed 36, 75, and 78 mutants at increasing resource limits. The first confirmatory run (C1-R2) failed before model execution because the provider rejected its response schema. After a schema-only repair made without viewing outcomes, a separately frozen follow-up run (C1-R3) completed 1,860 calls. The provider accepted 1,857 responses, but only nine passed the production semantic validator. The generation and execution rules did not match. We therefore preserve the run as an instrument-validation incident and report no prompt-effect estimate. This incident shows that provider or schema acceptance does not establish execution validity. Compilation and coverage are only diagnostics; the exact saved artifact must pass the full production path. A subsequent follow-up is excluded because it did not satisfy the preregistered evidence-completeness gate and is treated only as future work. We release the benchmark, failure-preserving contract, incident provenance, and governance controls needed to prevent infrastructure behavior from being misreported as model behavior.

Problem

• AI-Generated RTL Verification
• Trusted Execution
• Provider Schema
• Execution Validity
• Production Path

Innovation

• auditable framework
• hardware-security regressions
• production semantic validator
• instrument-validation incident
• governance controls