About This Resource

A toolkit for detecting and anonymizing sensitive information in text and other supported inputs. It provides configurable recognizers and transformations for workflows involving personal data.

Saved Notes

Original notes saved with this link. They may describe an earlier version.

Presidio - Data Protection and De-identification SDK

Presidio (Origin from Latin praesidium 'protection, garrison') helps to ensure sensitive data is properly managed and governed.

It provides fast identification and anonymization modules for private entities in text such as:

  • Credit card numbers
  • Names and locations
  • Social security numbers
  • Bitcoin wallets
  • US phone numbers
  • Financial data

Goals

  • Allow organizations to preserve privacy in a simpler way by democratizing de-identification technologies and introducing transparency in decisions
  • Embrace extensibility and customizability to a specific business need
  • Facilitate both fully automated and semi-automated PII de-identification flows on multiple platforms

Main Features

  1. PII Recognition: Predefined or custom recognizers using Named Entity Recognition, regular expressions, rule based logic and checksum with multi-language support
  2. External Integration: Connect to external PII detection models
  3. Flexible Deployment: Support for Python, PySpark, Docker and Kubernetes environments
  4. Customization: Configurable PII identification and de-identification
  5. Image Processing: Redact PII from images (including DICOM medical files)

⚠️ Note: While Presidio can identify sensitive/PII data in text, its automated detection is not guaranteed to find all sensitive information. Additional security measures are recommended.