Metraipolis › archive › dc_10d7bb0664e8

Redacting Personal Data: A Speed and Accuracy Comparison of Regex, Presidio and Hybrid Designs — arXiv:2611.07633

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.07633
License (as archived)
CC0-1.0
Archived
2026-11-06T14:41:41.091Z
SHA-256 of the archived text
5012d1df97e75f25cfcd2cf8621528e23d62f241300331e42911cef2263b9954
Stable URL of this page
https://metraipolis.com/documento/dc_10d7bb0664e8

How to cite

Redacting Personal Data: A Speed and Accuracy Comparison of Regex, Presidio and Hybrid Designs — arXiv:2611.07633 — arXiv (en), https://arxiv.org/abs/2611.07633 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_10d7bb0664e8 (Metraipolis archive dc_10d7bb0664e8, sha256 5012d1df97e75f25cfcd2cf8621528e23d62f241300331e42911cef2263b9954)
BibTeX
@misc{dc10d7bb0664e8,
  title = {Redacting Personal Data: A Speed and Accuracy Comparison of Regex, Presidio and Hybrid Designs — arXiv:2611.07633},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07633},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_10d7bb0664e8; sha256 5012d1df97e75f25cfcd2cf8621528e23d62f241300331e42911cef2263b9954},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07633. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Many enterprise projects now pass free text to large language models (LLMs), and that text often contains personally identifiable information (PII) such as names, phone numbers, email addresses, home addresses and dates of birth. Once a prompt is sent, this data is copied into provider systems, application logs and observability traces. Redacting PII before the call is an obvious control, yet teams seldom have numbers on what it costs in latency or what it lets through. This paper compares four redaction designs that any LLM pipeline can adopt: a pure regular-expression (regex) redactor, Microsoft Presidio running on a spaCy model, a hybrid in which Presidio finds only person names while regex handles structured identifiers, and a fast hybrid that calls spaCy's named-entity component directly. All four share a known-entity rule, which removes the person the system already knows it is handling, and a consistent placeholder scheme, so the LLM can still tell one person from another after redaction. We evaluate the designs on a sample workflow, which we call ProfileAssist, that turns resumes into structured profiles, using 100 synthetic resumes (523 characters on average, with 900 PII values and 600 business terms that must survive). Regex ran at a 0.20 ms median but caught only 88.9% of PII, because it cannot find names that are not known in advance, such as the references listed in a resume. Presidio, hybrid and fast hybrid each caught 100% of PII and kept 100% of business terms, at median latencies of 37.59 ms, 30.23 ms and 13.48 ms. Measured against a 9,120 ms median LLM call, even the slowest option adds only 0.41% to the request. We therefore recommend the fast hybrid as a default for LLM pipelines that handle personal data, with regex kept as a safety net rather than as the only control.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.07633 — 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 2026-11-06T14:18:42.642Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).