Skip to main content

Syft: Data Science in Python with privacy guarantees

30 minutes


In today’s data-driven world, privacy stands as an essential requirements for the ethical and effective practice of data science. Moreover, the implementation of robust privacy guarantees in data analysis not only protects sensitive information, but also unlocks the potential for unprecedented democratisation of models and datasets.

Syft is an open source stack that provides secure and private Data Science in Python. Syft decouples private data from model training, using techniques like Federated Learning, and Encrypted Computation. Moreover, Syft provides a numpy-like interface to integrate with deep learning frameworks so that it is easier to replicate any existing workflows while using privacy-enhancing techniques.

In the first part of my talk I will introduce PETs (Privacy Enhancing Technologies), and discuss OpenMined mission to democratise access to AI models and datasets. Afterwards, I will demonstrate how PySyft works, and how it can be used to run a machine learning experiments, with privacy guarantees.

The speaker

Valerio Maggio

Valerio Maggio

Valerio Maggio is a Researcher, and Education Lead at Open Mined. He is well versed in open science and research software, and he has been recently awarded a fellowship from the Software Sustainability Institute (profile) focused on developing open teaching modules on Privacy-Preserving Machine Learning. Valerio is also an open-source contributor, and an active member of the Python community, helping with the organisation of many international conferences and community meetups like PyCon Italy, PyData, EuroPython, and EuroSciPy. All his talks, workshop materials and random ramblings are publicly available on his Speaker Deck and GitHub profiles. In his free time, Valerio is a casual Magic: The Gathering wizard 🧙‍♂️, of course playing a community magic format.