---
title: "OpenAI Open-Sources Privacy Filter to Strip Sensitive Data Before It Reaches Any AI"
subtitle: "OpenAI open-sources a 1.5B-parameter PII detection model that runs locally, strips sensitive data in one pass, and hits 96% F1 out of the box"
url: "https://alphasignal.ai/news/openai-open-sources-privacy-filter-to-strip-sensitive-data-before-it-reaches"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "OpenAI"
company_url: "https://alphasignal.ai/company/openai"
published: "2026-04-22T19:55:02.000Z"
updated: "2026-08-15T07:10:33.979Z"
type: "Repo"
topics:
  - "Open Source"
  - "Security"
subtopics:
  - "Content Moderation"
upvotes: 1149
source_url: "https://github.com/openai/privacy-filter"
comments: 0
truncated: true
---

# OpenAI Open-Sources Privacy Filter to Strip Sensitive Data Before It Reaches Any AI

> OpenAI open-sources a 1.5B-parameter PII detection model that runs locally, strips sensitive data in one pass, and hits 96% F1 out of the box

OpenAI just open-sourced [Privacy Filter](https://openai.com/index/introducing-openai-privacy-filter/), a purpose-built model for detecting and redacting personally identifiable information (PII) in text. It runs entirely on your machine, processes up to 128,000 tokens in a single forward pass, and is free to use commercially under the Apache 2.0 license. The repo and weights are live on [GitHub](https://github.com/openai/privacy-filter) and Hugging Face right now.

The headline stat: Privacy Filter achieves state-of-the-art results on the PII-Masking-300k benchmark with an F1 score of 96%, rising to a corrected 97.43% after accounting for label noise in the dataset. That puts it well ahead of regex-based tools and older NER models on real-world text.

## The problem it actually solves

Every team building on top of LLMs eventually runs into the same wall: you want to send user data to a model, but that data contains names, emails, phone numbers, or API keys. The classic options are either regex patterns (brittle, easy to fool) or sending the text to a managed cloud service for de-identification (which defeats the purpose if data residency is the concern).

Privacy Filter is designed for high-throughput privacy workflows, and is able to perform context-aware detection of PII in unstructured text. It can run locally, which means that PII can be masked or redacted without leaving your machine. That last part is the whole point for regulated industries.

OpenAI also notes they use a fine-tuned version of Privacy Filter in their own internal privacy-preserving workflows, which is a meaningful signal about production readiness.

## What it detects

It detects eight categories of sensitive spans:

* `private_person` \- individual names
* `private_address` \- home and physical addresses
* `private_email` \- email addresses
* `private_phone` \- phone numbers
* `private_url` \- URLs tied to individuals
* `private_date` \- dates (e.g. birthdates)
* `account_number` \- credit card numbers, bank accounts, and similar
* `secret` \- API keys, passwords, credentials

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [Introducing OpenAI Privacy Filter](https://openai.com/index/introducing-openai-privacy-filter/)
- [GitHub - openai/privacy-filter](https://github.com/openai/privacy-filter)
- [openai/privacy-filter · Hugging Face](https://huggingface.co/openai/privacy-filter)
- [OpenAI Open-Sources Privacy Filter, a Tiny Model That Scrubs PII Without an API Call](https://hackernoon.com/openai-open-sources-privacy-filter-a-tiny-model-that-scrubs-pii-without-an-api-call)
- [OpenAI Releases Privacy Filter: A 1.5B-Parameter Open-Source PII Redaction Model](https://www.marktechpost.com/2026/04/28/openai-releases-privacy-filter-a-1-5b-parameter-open-source-pii-redaction-model-with-50m-active-parameters/)