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
This library helps data scientists and machine learning engineers train models while protecting individual user data. It takes your existing TensorFlow models and applies differential privacy techniques to the training process. The output is a privacy-preserving machine learning model suitable for deployment in sensitive applications.
About differential-privacy-library
IBM/differential-privacy-library
Diffprivlib: The IBM Differential Privacy Library
This project helps data scientists and researchers explore and experiment with differential privacy in machine learning and data analytics. You can feed in your standard datasets and get back models or data analyses that have privacy guarantees built-in. It's designed for anyone looking to understand or apply privacy-preserving techniques to their data-driven work.
Scores updated daily from GitHub, PyPI, and npm data. How scores work