PARSE: Provenance-Aware Retrieval Sanitization for Professional Domain LLM Agents

Prompt injection defenses evaluated on synthetic benchmarks do not generalize to real enterprise documents, which are longer, denser, and interleave legitimate authority language with factual content. We demonstrate this gap with a benchmark of 122 tasks across five professional domains (financial, legal, medical, scientific, DevOps) built on real retrieved documents -- actual SEC filings, Federal Register rules, PubMed abstracts, arXiv papers, and GitHub postmortems -- paired with LLM-generated tasks and camouflaged payloads that were not human-validated. Paraphrasing, the strongest defense on synthetic benchmarks, shows no statistically significant attack success rate reduction on real ...

<iframe src="https://silytics.si/embed/item/8b6328f6-8d5a-4009-9736-31b19d403efe" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.