Privacy Utils Differential Privacy

Differential Privacy mechanisms and utilities for privacy-preserving data analysis.

Features

• Laplace Mechanism: Add noise to numerical data
• Gaussian Mechanism: Advanced noise addition with better utility
• Exponential Mechanism: For discrete choice problems
• Privacy Budget Tracking: Monitor and manage privacy expenditure
• Composition Theorems: Combine multiple DP operations
• Sensitivity Analysis: Automatic sensitivity calculation

Installation

npm install privacy-utils-dp

Usage

import { LaplaceMechanism, PrivacyBudget, composeBudgets } from 'privacy-utils-dp';

// Create a privacy budget
const budget = new PrivacyBudget({ epsilon: 1.0, delta: 1e-5 });

// Add Laplace noise
const mechanism = new LaplaceMechanism({ sensitivity: 1.0 });
const noisyValue = mechanism.addNoise(42, budget);

// Compose multiple privacy budgets
const budget1 = new PrivacyBudget({ epsilon: 0.5, delta: 1e-6 });
const budget2 = new PrivacyBudget({ epsilon: 0.5, delta: 1e-6 });
const composedBudget = composeBudgets([budget1, budget2]);

// Check budget status
console.log(`Remaining epsilon: ${budget.remainingEpsilon}`);
console.log(`Budget exhausted: ${budget.isExhausted}`);

API Reference

For complete API documentation, see the TypeScript definitions or visit the main repository.

License

MIT

Contributing

Contributions are welcome! Please see the main repository for contribution guidelines.