Model Releases
Model Card for OpenAI Privacy Filter
arXiv:2608.18274v1 Announce Type: cross Abstract: OpenAI Privacy Filter is a compact, bidirectional token-classification model for detecting and redacting personally identifiable information (PII) and
arXiv:2608.18274v1 Announce Type: cross Abstract: 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.
Related
- Leaky Language Models: Stealing Architecture and Inference Optimizations via Per-Token Timing
- Distributed Deep Variational Approach for Privacy-preserving Data Release
- Private Generative Bootstrap via Blocking
- Adaptive Heterogeneous Compression for Resource-Efficient Federated Knowledge Distillation
Source: arXiv cs.LG | 2026-08-20