OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Security & Safety

Pii Masker

Pii Masker is a Python library that uses AI models, including DeBERTa-v3, to detect personally identifiable information in text, mask detected details with placeholders, and return structured PII data.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Pii Masker — OpenViST project profile in AI Security & Safety.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a Python text workflow needs an initial PII detection and masking step before analysis or model use.

Who it is for

  • Python developers handling text that may contain personal information.
  • Teams adding a PII-masking preprocessing step to data analysis or model-input workflows.

Documented uses

  • Detect names, addresses, phone numbers and other PII in text.
  • Replace detected details with placeholder labels.
  • Retrieve a structured dictionary of detected PII alongside masked text.
Before you choose

Requirements & limits

The repository describes the tool as open source and displays a Python 3.8+ badge. Its README provides dependency-installation and model-download instructions.

  • The documented default model is DeBERTa-v3; the README also describes a Longformer-based alternative with a Bi-LSTM head and 4,096-token sequence length.
  • Setup requires installing repository dependencies and downloading model files into a specified local directory.
  • The repository includes a RAG integration example using Milvus, which is a separate vector-database component.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Mask PII in a text string with the Python API

Use the documented `PIIMasker` API to mask PII in a sample text string and obtain its structured PII output.

Before you start

  • PII Masker installed and its model files prepared as described in the repository README.

Steps

  1. From the pii-masker directory, import and initialize the masker: from model import PIIMasker and masker = PIIMasker().

  2. Set a text string, such as John Doe lives at 1234 Elm St..

  3. Call masked_text, pii_dict = masker.mask_pii(text) and print masked_text.

Expected outcome

The README's example produces `[NAME] lives at [ADDRESS]` as masked text; the call also returns a structured PII dictionary.

Guide limitations

  • The README demonstrates a sample only; it does not specify broader accuracy, entity coverage, or validation procedures.
  • The sample setup and usage do not establish deployment targets.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
HydroXai/pii-masker · Official homepage title · retained in its source language
How we review sourcesSuggest a correction