Metraipolis › archive › dc_abf0a222cec8

Persona Guardrail: A Production-Grade Defense Framework for Agentic Systems — arXiv:2610.03434

Source
arXiv
Original
https://arxiv.org/abs/2610.03434
License (as archived)
CC0-1.0
Archived
2026-10-05T23:06:24.301Z
SHA-256 of the archived text
d31c6b61f99818504d0a3aa2fa541a8e63f7f6c8ead63e9e0aca4b196dce8481
Stable URL of this page
https://metraipolis.com/documento/dc_abf0a222cec8

How to cite

Persona Guardrail: A Production-Grade Defense Framework for Agentic Systems — arXiv:2610.03434 — arXiv, https://arxiv.org/abs/2610.03434 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_abf0a222cec8 (Metraipolis archive dc_abf0a222cec8, sha256 d31c6b61f99818504d0a3aa2fa541a8e63f7f6c8ead63e9e0aca4b196dce8481)
BibTeX
@misc{dcabf0a222cec8,
  title = {Persona Guardrail: A Production-Grade Defense Framework for Agentic Systems — arXiv:2610.03434},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03434},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_abf0a222cec8; sha256 d31c6b61f99818504d0a3aa2fa541a8e63f7f6c8ead63e9e0aca4b196dce8481},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03434. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model-based agents are increasingly deployed to perform domain-specific tasks by interacting with enterprise knowledge, tools, and external services. Existing runtime guardrails primarily target prompt injection and other attack-specific behaviors under a black-box threat model, but provide limited guarantees that agents operate within their intended functionality. As a result, production agents remain vulnerable to malicious requests and out-of-domain queries that existing defenses often fail to distinguish. We present Persona Guardrail, a production-grade runtime defense framework that enforces explicit functional boundaries for customer-facing agentic AI systems through synchronous input and output validation driven by semantic allowlist and blocklist specifications. We also introduce PAGE (Persona-Aware Guardrail Evaluation), a benchmark for evaluating function-specific guardrails across benign, adversarial, and out-of-domain interactions on both user and agent turns. Compared with a generic LLM-based guardrail, Persona Guardrail improves overall accuracy from 85.7% to 95.9%, increases out-of-domain detection from 57.3% to 93.5%, and reduces the false-approved rate from 25.0% to 4.7%. Currently deployed in production, Persona Guardrail meets its latency budget while sustaining a very low false-block and false-allow rate under realistic production workloads. These results demonstrate that Persona Guardrail provides a practical, scalable, and production-ready foundation for securing agentic AI systems.

Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2610.03434 — 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 2026-10-05T23:01:08.546Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).