Metraipolis › archive › dc_3ee4054bedba

Structured Decomposition for Reliable LLM-Generated Access Control Policies — arXiv:2609.24036

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.24036
License (as archived): CC0-1.0
Archived: 2026-10-09T07:01:19.040Z
SHA-256 of the archived text: 01e001e4b7385893638a64d7f76c1c9a8b84f4baf14bfde0a866fe75e8be60dd
Stable URL of this page: https://metraipolis.com/documento/dc_3ee4054bedba

How to cite

Structured Decomposition for Reliable LLM-Generated Access Control Policies — arXiv:2609.24036 — arXiv (en), https://arxiv.org/abs/2609.24036 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3ee4054bedba (Metraipolis archive dc_3ee4054bedba, sha256 01e001e4b7385893638a64d7f76c1c9a8b84f4baf14bfde0a866fe75e8be60dd)

BibTeX

@misc{dc3ee4054bedba,
  title = {Structured Decomposition for Reliable LLM-Generated Access Control Policies — arXiv:2609.24036},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24036},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3ee4054bedba; sha256 01e001e4b7385893638a64d7f76c1c9a8b84f4baf14bfde0a866fe75e8be60dd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24036. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper presents an LLM-based system that translates natural-language access control policies (NLACPs) into executable Rego code for Open Policy Agent (OPA). It provides a modular, end-to-end pipeline for policy detection, component extraction, schema validation, linting, compilation, and automated test generation and execution. The system is designed to bridge the gap between human-readable access requirements and machine-enforceable policy-as-code (PaC), with a focus on deployment reliability and security correctness. We evaluate the system on 372 ACRE-complete access control statements with non-null subject, action, and resource annotations against a direct single-prompt LLM baseline to isolate the contribution of structured decomposition and schema-aware validation. The system achieves a 50.3% end-to-end policy correctness rate, compared with 15.3% for the baseline, representing a 3.3x improvement. A policy is counted as correct only if it satisfies compilation, linting, and both positive and negative tests, making this a strict measure of deployable correctness. On security-critical patterns, the system generates correct deny semantics for 87.5% of deny policies (baseline: 37.5%), ownership conditions for 100% of ownership-qualified policies (baseline: 40%), and status-qualified conditions for 100% of status-qualified policies (baseline: 55.6%). These results indicate that structured decomposition and schema-aware validation play a critical role in improving the reliability of LLM-generated authorization policies.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CR).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2609.24036 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T06:56:01.032Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).