轻量级模型一键检测并擦除文本中的隐私信息
Model Card for OpenAI Privacy Filter
- 基于双向注意力机制，单次前向传播完成隐私识别
- 15亿参数，支持12.8万词长上下文，每词仅激活5000万参数
- 可配置精度召回权衡，适合本地部署和领域微调
OpenAI Privacy Filter 是一个紧凑的双向标记分类模型，用于检测并擦除非结构化文本中的个人身份信息（PII）和敏感内容。该模型源自自回归预训练检查点，转换为双向、带状注意力分类器，可在单次前向传播中对输入序列进行标签标注。受限Viterbi解码器生成八个隐私类别的一致片段，并提供可配置的精确率-召回率权衡点。模型总参数量为15亿，每词激活5000万参数，支持128,000词的上下文窗口。设计用于高效本地部署与领域特定微调，作为分层隐私工作流中的可配置数据最小化组件，而非匿名化或合规保证。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。