curtain-privacy

On-device PII redaction: a 14.2 MB token classifier plus deterministic recognizers across 24 Latin-script languages, with a reversible-placeholder layer for chat. It runs in the browser, in Node, and on iOS and Android from these same files. Source, training pipeline, whitepaper, and the full model card: https://github.com/hackshare/curtain-privacy

The model is built locally from the committed train/ pipeline; this repo is a distribution copy. Verify integrity by pinning a revision and checking the hash: onnx/model_q4.onnx SHA-256 24ba1f03a8c3db8a4f760d4d266faeb679ba23f8c23f7be9ba6964cbfff6f6c1.

Integrating

Web and Node (transformers.js)

import { createGuard } from "curtain-privacy";

const guard = await createGuard({ model: "hackshare/curtain-privacy", revision: "v1.0.0" });
const { text } = await guard.protect("My SSN is 472-81-0094");

revision: "v1.0.0" pins the audited weights. transformers.js fetches from this repo with permissive CORS, so it works from any origin. v1.0.0 is a moving pointer to the latest build; to pin an immutable artifact, use the timestamped tag v1.0.0-<timestamp> published alongside each release.

iOS and Android (ONNX Runtime Mobile)

Fetch or bundle two files from a pinned revision:

• https://huggingface.co/hackshare/curtain-privacy/resolve/v1.0.0/onnx/model_q4.onnx
• https://huggingface.co/hackshare/curtain-privacy/resolve/v1.0.0/tokenizer.json

Verify model_q4.onnx against the SHA-256 above. Load the model with ONNX Runtime Mobile, tokenize with the Hugging Face tokenizers library (Swift and Kotlin bindings load tokenizer.json directly) or ONNX Runtime Extensions, then apply the BIO decode and the default keep-set (CITY, STATE, ZIP_CODE) the library documents. These are integration guides, not a shipped native SDK.