tf-encrypted

“TensorFlow Federated (TFF) is an open-source framework for machine learning and other computations on decentralized data. TFF has been developed to facilitate open research and experimentation with Federated Learning (FL), an approach to machine learning where a shared global model is trained across many participating clients that keep their training data locally. For example, FL has been used to train prediction models for mobile keyboards without uploading sensitive typing data to servers.“ From https://www.tensorflow.org/federated This is a very exiciting project that compliments other privacy-preserving machine learning techniques (PPML) in TensorFlow: - Differential Privacy: https://github.com/tensorflow/privacy - Secure Multi-Party Computation: https://github.com/mortendahl/tf-encrypted - Confidential Computing (Trusted Execution E

SecureNN gives efficient secure ReLU's and Maxpooling neural network layers. This is done using secure multiparty computation (MPC). tf-encrypted is a project that aims to bring secure technologies into a place that feels familiar to practitioners. You can read more about tf-encrypted here: https://medium.com/dropoutlabs/experimenting-with-tf-encrypt... and the project github here: https://github.com/mortendahl/tf-encrypted

Hello everyone, we also have the supporting code we used on GitHub [1] as well as a higher level blog post published on Medium [2]. [1] https://github.com/mortendahl/tf-encrypted [2] https://medium.com/dropoutlabs/experimenting-with-tf-encrypt...