September 13-16, 2022
Dublin, Ireland + Virtual
View More Details & Registration
Note: The schedule is subject to change.

The Sched app allows you to build your schedule but is not a substitute for your event registration. You must be registered for Open Source Summit Europe 2022 to participate in the sessions. If you have not registered but would like to join us, please go to the event registration page to purchase a registration.

This schedule is automatically displayed in Irish Standard Time (UTC +1). To see the schedule in your preferred timezone, please select from the drop-down menu to the right, above "Filter by Date."

IMPORTANT NOTE: Timing of sessions and room locations are subject to change.

Back To Schedule
Tuesday, September 13 • 16:15 - 16:55
BlindAI, an Open-source Solution for Privacy-friendly AI Deployment - Daniel Huynh, Mithril Security

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
Confidential Computing is a recent technology that enables end-to-end encryption when analyzing sensitive data. As such, data owners can share their data to AI companies, for instance to train or consume an AI model, without ever risking their data being stolen, leaked or used for any other purpose, as data remains protected even when shared to third parties. That is why we have launched BlindAI, an Open-source project, aiming to democratize privacy-friendly AI. We leverage Confidential Computing to provide end-to-end protection guarantees, even when sending data to be analyzed by third parties. Our solution currently supports confidential deployment of ONNX models. This workshop aims to introduce the high level principles of Confidential Computing. We will show how BlindAI can be used to deploy privacy friendly AI models, including Transformers for confidential document analysis, and ResNets for medical imaging. The workshop will be organized in the following manner: - Presentation of the current challenges - Introduction to Confidential Computing - Demonstration of Confidential AI deployment with BlindAI

avatar for Daniel Huynh

Daniel Huynh

CEO, Mithril Security
- Leads the development of an open-source state-of-the-art AI inference server for confidential data, requiring software engineering, cyber-security and data science expertise - Manages the product, turns market insights and customer feedback into technical features - Wrote several... Read More →

Tuesday September 13, 2022 16:15 - 16:55 IST
Liffey Meeting Room 3 (Level 1)
  Open AI & Data Forum, Security and Privacy