PII Detector

OfficialPRO

Identify documents containing personally identifiable information.

📄 pdf📊 office📧 email

34.1K downloads

89 stars

2 months ago

Description

The PII Detector helps organizations maintain GDPR and CCPA compliance by identifying documents that may contain personally identifiable information, without reading the content. Essential for: - GDPR compliance audits - Data classification initiatives - Privacy impact assessments - Document retention policies

Quick Start

Install via CLI:

veriafy pull veriafy/pii-detector

Use in Python:

from veriafy import Veriafy

client = Veriafy()
result = client.classify("document.pdf", model="veriafy/pii-detector")

print(result.categories)  # Classification results
print(result.confidence)  # Confidence score

Classification Categories

no_pii

No PII detected

low_pii

Contains minimal PII

high_pii

Contains significant PII

Benchmarks

96.8%

Accuracy

95.9%

Precision

97.6%

Recall

96.7%

F1 Score

Model Information

Version: 1.5.0
Size: 94 MB
License: Commercial
Created: May 2024
Updated: 2 months ago

Requirements

CPU: 2 cores
RAM: 4 GB
GPU: Optional

Resources

Python SDK Reference CLI Documentation How Models Work