Differential Privacy
by Community · free · Last verified 2026-03-17
Provides mathematically rigorous privacy guarantees by adding calibrated noise to query outputs or model gradients, ensuring individual data points cannot be inferred from published statistics or trained models. The de facto standard for privacy-preserving data analysis and compliant ML training.
https://opacus.ai/ ↗B
B—Above Average
Adoption: B+Quality: AFreshness: ACitations: AEngagement: F
Specifications
- License
- Apache-2.0
- Pricing
- free
- Capabilities
- DP-SGD-training, local-differential-privacy, Gaussian-mechanism, Laplace-mechanism, privacy-budget-accounting
- Integrations
- Opacus, TensorFlow Privacy, Google DP Library, IBM diffprivlib
- Use Cases
- GDPR-compliant model training on sensitive data, Privacy-preserving census analytics, Secure federated model aggregation
- API Available
- No
- Difficulty
- advanced
- Prerequisites
- probability-theory, machine-learning, cryptography-basics
- Supported Agents
- Tags
- privacy, differential-privacy, noise-injection, privacy-preserving-ml
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
66.8Adoption
70
Quality
88
Freshness
83
Citations
85
Engagement
0