Presidio

Paket

Open-source library for detecting and anonymizing PII in text and images

Fiyat
Free, open source
Erişim
None, runs locally

Hakkında

Python framework that finds PII such as names, phone numbers, card numbers and national IDs with NER, regex and checksums, then masks, replaces or encrypts it. Runs locally or as Docker services. Now community-run by Data Privacy Stack; it can miss some PII.

Neler yapabilirsin

  • Detect names, phone numbers, emails and card numbers in free text
  • Redact, mask, hash or encrypt PII before text reaches an LLM or a log
  • Redact PII burned into images and DICOM medical scans

Başlarken

  1. pip install presidio-analyzer presidio-anonymizer
  2. python -m spacy download en_core_web_lg

Örnek kod

from presidio_analyzer import AnalyzerEngine
from presidio_anonymizer import AnonymizerEngine

text = "My phone number is 212-555-5555"
results = AnalyzerEngine().analyze(text=text, entities=["PHONE_NUMBER"], language="en")
print(AnonymizerEngine().anonymize(text=text, analyzer_results=results).text)
# My phone number is <PHONE_NUMBER>

Ayrıntılar

Barındırma
Kendi sunucunda, Kendi bilgisayarında
Kullanılabildiği yerler
Tüm dünya
Resmi SDK'lar
Python
MCP sunucusu
Yok

Görevler

Alternatifler

Aynı görevler için başka araçlar.

Son kontrol: .