Metraipolis › archive › dc_dd4c8bf53593

Model Card for OpenAI Privacy Filter — arXiv:2608.18274

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.18274
License (as archived)
CC0-1.0
Archived
2026-10-18T13:51:48.313Z
SHA-256 of the archived text
b91646576ff577d6b54d1142bda3208a1327e5c2a4456afb2addd38d870c5e5b
Stable URL of this page
https://metraipolis.com/documento/dc_dd4c8bf53593

How to cite

Model Card for OpenAI Privacy Filter — arXiv:2608.18274 — arXiv (en), https://arxiv.org/abs/2608.18274 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dd4c8bf53593 (Metraipolis archive dc_dd4c8bf53593, sha256 b91646576ff577d6b54d1142bda3208a1327e5c2a4456afb2addd38d870c5e5b)
BibTeX
@misc{dcdd4c8bf53593,
  title = {Model Card for OpenAI Privacy Filter — arXiv:2608.18274},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18274},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dd4c8bf53593; sha256 b91646576ff577d6b54d1142bda3208a1327e5c2a4456afb2addd38d870c5e5b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18274. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

OpenAI Privacy Filter is a compact, bidirectional token-classification model for detecting and redacting personally identifiable information (PII) and secrets in unstructured text. The model is derived from an autoregressively pretrained checkpoint and converted into a bidirectional, banded-attention classifier that labels an input sequence in a single forward pass. A constrained Viterbi decoder produces coherent spans across eight privacy categories and exposes configurable operating points for precision-recall tradeoffs. Privacy Filter has 1.5 billion total parameters, 50 million active parameters per token, and a 128,000-token context window. It is designed for efficient local deployment and domain-specific fine-tuning. Privacy Filter is intended as a configurable data-minimization component within layered privacy workflows, not as an anonymization or compliance guarantee.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-08-20 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.18274 — 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 2026-10-18T13:49:54.220Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).