Rizzo-AI-Academy/rizzo-pii

Use frontier models without giving up your data.

📄 Read the full technical report (PDF) — model, dataset, method and experiments in detail

🪟 Windows installer · 🍎 macOS (Apple Silicon) · 🐧 Linux AppImage — all available now

rizzo-pii:0.3B is a lightweight, CPU-friendly, Italian-first token-classification model (≈0.3B parameters, mmBERT / ModernBERT backbone) that detects 22 categories of personal data — including the Italian-legal identifiers (codice fiscale, partita IVA, dati catastali) that no other open model covers — and drives a fully reversible anonymization workflow:

🔒 anonymize locally → 🏷️ placeholder + reversible local dictionary → ☁️ frontier LLM → 🔓 restore locally

It is built for law firms, accountants, notaries and anyone bound by the GDPR who wants to keep using ChatGPT / Claude / Gemini on sensitive documents without ever sending the real data out.

People summarize contracts, draft replies and ask legal questions simply by pasting the document in. It is fast and useful — and it quietly moves enormous amounts of personal and confidential data off the user's device. Names, addresses, tax codes, IBANs, health details, unsigned-contract clauses: all of it crosses the network to servers the user does not control, where it may be logged, cached, retained or exposed in a breach. For a law firm or a hospital this is not hypothetical; under the GDPR it can be a direct compliance failure.