SOURCE-LINKED INTELLIGENCE

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

arXiv · Artificial Intelligence · article · Sep 17, 2026 · UTC

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 o

Read original source ↗ Open in workspace

recordType: paper
region: Global

Evidence & attribution

arXiv · AI, language, vision and robotics · 2026-09-17T07:54:54.000Z
arXiv · Artificial Intelligence · 2026-09-17T07:54:54.000Z

First collected: 2026-09-19T20:26:32.566Z. This is not the publication date.