Presidio — PII Detection & Anonymization

Presidio — PII Detection & Anonymization

Microsoft Presidio provides fast, contextual analysis and anonymization of personally identifiable information (PII) in text and images. It powers data-privacy compliance in LLM pipelines, ETL workflows, and document processing systems.

Key Features

• 50+ built-in recognisers: names, emails, phone numbers, SSN, credit cards, IBANs, IP addresses, medical identifiers, and more
• Custom recogniser support (regex, spaCy NER, stanza, transformer models)
• Anonymization operators: redact, replace, hash, encrypt, mask, synthetic data substitution
• Image redaction module (DICOM, PDF, raster)
• REST API (presidio-analyzer + presidio-anonymizer as microservices)

Quick Start

from presidio_analyzer import AnalyzerEngine
from presidio_anonymizer import AnonymizerEngine

analyzer = AnalyzerEngine()
results = analyzer.analyze(text="My phone is 212-555-1234", language="en")
anonymizer = AnonymizerEngine()
print(anonymizer.anonymize(text="My phone is 212-555-1234", analyzer_results=results))
# Output: My phone is <PHONE_NUMBER>

npx ai-supply add presidio-pii-anonymizer

Curated mirror of the open-source Presidio (MIT). Get it from the source.