What started out as a side project less than two years ago is growing up and moving into its own organization on GitHub and own Slack!

The tremendous growth we have seen would not have been possible without partner contributors, and with this move TF Encrypted is being cemented as an independent community project that can encourage participation and remain focused on its mission: getting privacy-enhancing tools into the hands of machine learning practitioners.

A Framework for Encrypted Deep Learning

TF Encrypted makes it easy to apply machine learning to data that remains encrypted at all times. It builds on, and integrates heavily, with TensorFlow, providing…


A Library for Private Machine Learning in TensorFlow

with Jason Mancuso at Dropout Labs.

Privacy-preserving machine learning offers many benefits and interesting applications: being able to train and predict on data while it remains in encrypted form unlocks the utility of data that were previously inaccessible due to privacy concerns. But to make this happen several technical fields must come together, including cryptography, machine learning, distributed systems, and high-performance computing.

The TF Encrypted open source project aims at bringing researchers and practitioners together in a familiar framework in order to accelerate exploration and adaptation. …


and an open source Rust library

with Mario Cornejo and Mathieu Poumeyrol at Snips.

Today we’re open sourcing our experimental implementation of the Paillier homomorphic encryption scheme, written in Rust by our small team at Snips working on various privacy enhancing technologies.

Testing its performance we are not only interested in the concrete numbers we can achieve, but also in the price we pay for using a modern language (spoiler: Rust performed as well as C in all tests).

In the name of reproducibility we also share all our benchmarking code, including instruction for how to launch it on a Google GCE instance.

Security disclaimer: this…


and an open source Rust library

Today we’re happy to announce the open sourcing of our lightweight pure-Rust library for high-volume secret sharing!

There already exist many implementations of what’s called Shamir’s secret sharing, but it turned out that for sharing a high volume of secrets, this is not always the best choice. As a result, we decided to implement a packed variant, with a focus on keeping it lightweight and efficient. To also achieve a high degree of portability we wrote it in Rust, and since we want to experiment with it in several applications we kept it as a self-contained library.

In a later…


by Morten Dahl and Joseph Dureau @ Snips

Awareness, industry standards, as well as legislation around privacy are making steady progress, turning privacy into a strategic and ethical positioning. Large companies, such as Google and Apple, have taken into account these opportunities and constraints, and are setting high standards in the field.

Although there are some pragmatic solutions like storing limited amounts of data, removing unique identifiers, periodically erasing databases, etc., we would all prefer privacy to be based on mathematical properties.

Differential privacy (or DP for short) is an interesting solution to this problem. The idea behind it is that you want to add noise to the…

Morten Dahl

Privacy-preserving machine learning; see more on mortendahl.github.io

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store