Metraipolis › archive › dc_73bf183ca16b

ASIRF: An Agentic Framework for Context-Dependent Sensitive Information Redaction — arXiv:2609.29191

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.29191
License (as archived): CC0-1.0
Archived: 2026-10-08T04:26:04.122Z
SHA-256 of the archived text: 20fc9ea9b1b9f0d3853a0a20971997f92354daf2dcd657d9869874e8be0b2d13
Stable URL of this page: https://metraipolis.com/documento/dc_73bf183ca16b

How to cite

ASIRF: An Agentic Framework for Context-Dependent Sensitive Information Redaction — arXiv:2609.29191 — arXiv (en), https://arxiv.org/abs/2609.29191 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_73bf183ca16b (Metraipolis archive dc_73bf183ca16b, sha256 20fc9ea9b1b9f0d3853a0a20971997f92354daf2dcd657d9869874e8be0b2d13)

BibTeX

@misc{dc73bf183ca16b,
  title = {ASIRF: An Agentic Framework for Context-Dependent Sensitive Information Redaction — arXiv:2609.29191},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29191},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_73bf183ca16b; sha256 20fc9ea9b1b9f0d3853a0a20971997f92354daf2dcd657d9869874e8be0b2d13},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29191. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Sensitive information is defined by domain and intent, not a universal category, yet redaction systems such as privacy filters and named-entity recognizers fix a taxonomy at training time, requiring retraining for each new domain. We introduce ASIRF (Agentic Sensitive Information Redaction Framework), which retrieves domain-specific definitions based on the input's domain from a flexible knowledge base at inference time, needing no retraining to adapt. Two architectures, a three-call multi-agent pipeline and a single-agent variant, are evaluated across ten small open-weight models and eight datasets, including out-of-distribution fictional domains, against the OpenAI Privacy Filter (OPF) as a trained-classifier baseline. With only a few dozen expert-authored definitions per domain and no training data, ASIRF's recall exceeds OPF's in 68 of 80 model-domain combinations (85 percent), by at least one of the two architectures, with shortfalls confined mostly to OPF's training-distribution domains.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Information Retrieval (cs.IR); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.29191 — 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 2026-10-08T03:50:57.740Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).