TensorFlow Privacy
by Google · open-source · Last verified 2026-04-15
TensorFlow Privacy is a library that makes it easier to train machine learning models with differential privacy. It provides TensorFlow optimizers that implement differentially private stochastic gradient descent (DP-SGD), allowing developers to protect the privacy of training data while still achieving good model performance.
https://github.com/tensorflow/privacy ↗B+
B+—Good
Adoption: B+Quality: AFreshness: B+Citations: BEngagement: B
Specifications
- License
- Apache 2.0
- Pricing
- open-source
- Capabilities
- differentially private training, DP-SGD, privacy analysis
- Integrations
- TensorFlow, Keras
- Use Cases
- healthcare, finance, federated learning, sensitive data analysis
- API Available
- Yes
- Tags
- differential privacy, privacy-preserving ML, tensorflow, machine learning
- Added
- 2026-04-15
- Completeness
- 100%
Index Score
72.2Adoption
75
Quality
85
Freshness
70
Citations
65
Engagement
60