Metraipolis › archive › dc_eb792c775bf7

PolicyGuard: Prompt-Configurable Semantic DLP for LLM Coding Agents — arXiv:2608.02687

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.02687
License (as archived): CC0-1.0
Archived: 2026-10-31T12:34:19.730Z
SHA-256 of the archived text: 052591f22608cb3c9c7059c0a32b3f53830837c1b17f7992c75d2f993fefeeff
Stable URL of this page: https://metraipolis.com/documento/dc_eb792c775bf7

How to cite

PolicyGuard: Prompt-Configurable Semantic DLP for LLM Coding Agents — arXiv:2608.02687 — arXiv (en), https://arxiv.org/abs/2608.02687 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eb792c775bf7 (Metraipolis archive dc_eb792c775bf7, sha256 052591f22608cb3c9c7059c0a32b3f53830837c1b17f7992c75d2f993fefeeff)

BibTeX

@misc{dceb792c775bf7,
  title = {PolicyGuard: Prompt-Configurable Semantic DLP for LLM Coding Agents — arXiv:2608.02687},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.02687},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eb792c775bf7; sha256 052591f22608cb3c9c7059c0a32b3f53830837c1b17f7992c75d2f993fefeeff},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.02687. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI coding agents accept free-form natural language prompts that may inadvertently contain credentials, personally identifiable information (PII), or proprietary business data. Existing data loss prevention (DLP) solutions rely on rigid regex patterns, model fine-tuning, or vendor-managed classifiers with limited customizability. We present PolicyGuard, a pre-model interception framework that classifies user prompts using an LLM guided by a natural language policy file. Our key contributions are: (1) the policy-as-prompt paradigm, where DLP classification criteria are defined entirely in a plaintext policy document editable by non-engineers without code changes or model retraining; (2) a sealed evaluation protocol with template-family-level data splits, hidden holdouts, and frozen test sets to rigorously assess generalization; and (3) a comprehensive empirical evaluation across 2,000 multilingual prompts demonstrating 96.5% effective block rate (EBR) with only 3.0% false positive rate (FPR) on a frozen test set of 927 prompts, and perfect 100% accuracy on a 217-prompt hidden holdout. Information-matched baseline experiments show that PolicyGuard's natural language format significantly outperforms equivalent content in JSON format (McNemar chi-squared = 31.58, p < 0.001) and dramatically outperforms zero-shot classification (Cohen's h = 0.915). Cross-model portability experiments demonstrate that the same policy achieves 86.4-96.5% EBR across four different LLMs without modification.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-08-05 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR) ; Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2608.02687 — 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 2026-10-31T12:21:50.542Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).