Welcome to SecureML Documentation

Privacy-Preserving Machine Learning Made Simple

SecureML is a Python library that enables machine learning engineers to build and deploy models while maintaining compliance with privacy regulations like GDPR, CCPA, and HIPAA.

The library provides tools for:

• Data Anonymization: K-anonymity, pseudonymization, and data masking

• Privacy-Preserving Training: Differential privacy and federated learning

• Synthetic Data Generation: Create realistic but private datasets

• Compliance Checking: Automated compliance verification

• Audit Trails: Comprehensive logging for documentation

Contents:

• Installation
  • Requirements
  • Basic Installation
  • Using Poetry
  • Optional Components
  • Isolated Environments
  • Development Installation
  • Verifying Installation
• Quickstart
  • Data Anonymization
  • Differential Privacy Training
  • Synthetic Data Generation
  • Compliance Checking
  • Using the CLI
  • Next Steps
• User Guide
  • Anonymization
  • Differential Privacy
  • Synthetic Data
  • Compliance
  • Federated Learning
  • Audit Trails
  • Reporting
  • Key Management
  • Command-Line Interface
  • Isolated Environments
  • Overview
• Examples
  • Anonymization Examples
  • Compliance Checking Examples
  • Audit Trail Examples
  • Differential Privacy Examples
  • Federated Learning Examples
  • Synthetic Data Generation Examples
  • Report Generation Examples
  • CLI Examples
• API Reference
  • Differential Privacy API
  • Federated Learning API
  • Anonymization API
  • Synthetic Data API
  • Compliance API
  • Audit Trail API
  • Reporting API
  • Key Management API
  • CLI Extension API

Indices and tables

• Index

• Module Index

• Search Page