privacy and differential-privacy-library
These are complementary tools: TensorFlow Privacy provides privacy-preserving training mechanisms integrated into TensorFlow's computation graphs, while Diffprivlib offers model-agnostic differential privacy algorithms that can be applied to any ML framework, making them useful together for layered privacy protection.
About privacy
tensorflow/privacy
Library for training machine learning models with privacy for training data
Provides differentially private TensorFlow optimizers (SGD, Adam, etc.) with per-example gradient clipping and built-in privacy accounting tools to measure epsilon/delta guarantees. Includes optimized Keras implementations for Dense and Embedding layers that achieve DP training without meaningful performance overhead by leveraging fast per-example gradient computation. Integrates directly with TensorFlow 2.x and tf.keras, with tutorials demonstrating how to wrap standard optimizers into privacy-preserving variants.
About differential-privacy-library
IBM/differential-privacy-library
Diffprivlib: The IBM Differential Privacy Library
Scores updated daily from GitHub, PyPI, and npm data. How scores work