OpenAI 发布了“隐私过滤器”（Privacy Filter），这是一款开源的 AI 模型，可在本地运行，并在进一步处理文本之前自动删除其中的个人数据。
该模型能够检测八类数据，包括姓名、地址和密码，可处理长文档，并提供可调节的脱敏灵敏度。允许商业使用。
由于该模型无法保证符合法律要求的匿名化处理，且在处理非英文文本时存在困难，OpenAI 建议在敏感用例中进行人工审核。
OpenAI 发布了 Privacy Filter，这是一款旨在检测并删除文本中个人数据的开源模型。
据 OpenAI 称，Privacy Filter 专为那些需要在进一步处理前清洗大量文本的团队而设计，无论是用于训练自己的 AI 模型，还是与第三方共享数据。OpenAI 表示，该模型相对较小，仅有 15 亿参数，每次请求仅激活 5000 万参数，可在笔记本电脑甚至直接在浏览器中运行。该模型明确支持在本地硬件上运行，无需任何云端连接。
该模型可检测八类敏感内容：姓名、地址、电子邮件地址、电话号码、URL、日期、账号以及其他秘密信息（如密码或 API 密钥）。与传统聊天机器人不同，它不会生成新文本。相反，它会对输入内容进行一次遍历，并标记出哪些部分属于哪一类别。据 OpenAI 称，12.8 万个模型 token 的上下文窗口使其能够处理长文档而无需拆分。
用户可以调整设置，以控制模型是激进地脱敏（高召回率，更多误报）还是保守地脱敏（更少误报，但遗漏更多）。拥有自己数据集的团队还可以进一步微调该模型。
Privacy Filter 已在 GitHub 和 Hugging Face 上以 Apache 2.0 许可证发布，并允许商业使用。
敏感用例的明确限制
OpenAI 明确表示，隐私过滤器不提供任何法律意义上的匿名化或合规性保证。该模型仅旨在作为更广泛数据保护策略中的一个环节。OpenAI 自身列出了若干弱点：罕见或地域性不常见的姓名更易被遗漏，知名公众人物或组织有时会被错误编辑，且在处理非英语文本或非拉丁字母时性能会下降。
对于医疗、法律、金融或人力资源等敏感领域，OpenAI 明确建议保留人工审核环节。此外，标签类别无法在运行时更改，这意味着需要不同策略的团队必须对模型进行微调。
OpenAI has published "Privacy Filter," an open-source AI model that runs locally and automatically redacts personal data from text before further processing.
The model detects eight data categories including names, addresses, and passwords, handles long documents, and offers adjustable redaction sensitivity. Commercial use is permitted.
Since the model doesn't guarantee legally compliant anonymization and struggles with non-English text, OpenAI recommends human review for sensitive use cases.
OpenAI has released Privacy Filter, an open-source model designed to detect and redact personal data in text.
According to OpenAI, Privacy Filter is built for teams that need to clean large volumes of text before processing it further, whether for training their own AI models or sharing data with third parties. The model is relatively small at 1.5 billion parameters, uses only 50 million active parameters per request, and runs on a laptop or even directly in a browser, OpenAI says. Running it on local hardware without any cloud connection is explicitly supported.
The model detects eight categories of sensitive content: names, addresses, email addresses, phone numbers, URLs, dates, account numbers, and other secrets like passwords or API keys. Unlike traditional chatbots, it doesn't generate new text. Instead, it makes a single pass through the input and labels which parts belong to which category. A 128,000-token context window lets it process long documents without splitting them up, according to OpenAI.
Users can adjust settings to control whether the model redacts aggressively (high recall, more false positives) or conservatively (fewer false positives, but more missed items). Teams with their own datasets can also fine-tune the model further.
Privacy Filter is available under the Apache 2.0 license on GitHub and Hugging Face, and commercial use is permitted.
Clear limits for sensitive use cases
OpenAI is clear that Privacy Filter does not provide any legal guarantee of anonymization or compliance. The model is meant to be just one layer in a broader data protection strategy. OpenAI itself lists several weaknesses: rare or regionally uncommon names are more likely to be missed, well-known public figures or organizations sometimes get incorrectly redacted, and performance drops with non-English text or non-Latin scripts.
For sensitive fields like healthcare, law, finance, or human resources, OpenAI explicitly recommends keeping human review in the loop. The label categories also can't be changed at runtime, meaning that teams that need a different policy will have to fine-tune the model.