09-19, 14:40–15:15 (Europe/Amsterdam), Escher
This talk is about data science on encrypted data with Python and Fully Homomorphic Encryption (FHE). FHE is a groundbreaking technology that secures data while preserving its utility, allowing data owners to process it even in its encrypted state. This talk will show how Concrete ML, a Python framework for data science with FHE, makes it easy to convert machine learning models to work with encrypted data, without knowing anything about cryptography.
The talk is addressed to privacy-minded Python developers that want to learn what is possible to build with FHE and how to build privacy and confidentiality features into their software. The talk is informative and assumes some participants have some data science knowledge. A first part will focus on use-cases and a second part on using Concrete ML in conjunction with other Python data processing libraries to implement the use-cases.
Attendees will learn why FHE is useful, in which use-cases it applies and how tools make it easy to work with FHE. Additionally they will discover what the current limitations are and what the future will bring.
Andrei Stoian obtained a Engineering degree in Computer Systems from the Politehnica University of Bucharest, then a PhD in Machine Learning for image and video analysis at the Conservatoire National des Arts et Metiers in Paris, France, in 2015. Since 2021 he has been working for Zama on building Concrete-ML, a machine learning toolkit to perform model inference on encrypted data. His research interests are centred on adapting deep learning models to FHE computation, especially in the areas of image classification and recognition. He has published more than 20 papers on various machine learning topics and holds several patents.