← Back to brief
ResearchOfficialPreprintarXiv Cryptography and Security

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

A new preprint demonstrates that prompt injection defenses tested on synthetic benchmarks do not generalize to real enterprise documents, which are longer and more complex. The authors introduce PARSE, a domain-aware sanitization pipeline that reduces prompt injection attack success rates by 38% compared to baseline methods, while maintaining near-baseline utility on real-world tasks across five professional domains.

Why it matters: This work exposes the limitations of synthetic security benchmarks and provides a practical, statistically validated defense for LLM agents operating on real enterprise data.

Full story at: arXiv Cryptography and Security