22:47Encrypted Computation: What if Decryption Wasn’t Needed? • Katharine Jarmul • GOTO 2024
From the creator
This presentation was recorded at GOTO Copenhagen 2024. #GOTOcon #GOTOcph https://gotocph.com Katharine Jarmul - Principal Data Scientist at Thoughtworks & O'Reilly Author @ProbablyPrivate RESOURCES https://twitter.com/kjam https://linkedin.com/in/katharinejarmul https://github.com/kjam https://kjamistan.com https://probablyprivate.com Links https://www.tooltester.com/en/blog/chatgpt-statistics https://huggingface.co https://github.com/tf-encrypted/moose https://github.com/apple/swift-homomorphic-encryption https://github.com/zama-ai https://github.com/carbynestack ABSTRACT If you are curious about the field of cryptography and what it has to offer data science and machine learning, this talk is for you! We'll dive into the field of encrypted computation, where decryption isn't needed in order to perform calculations, transformations and operations on the data. You'll learn some of the core mathematical theory behind why and how this works, as well as the differences between approaches like homomorphic encryption and secure multi-party computation. At the end, you'll get some pointers and open-source library hints on where to go next and how to start using encrypted computation for problems you are solving the hard way (or not solving at all). [...] TIMECODES 00:00 Intro 03:18 What if...? 04:23 Demo: Huggingface 06:25 Homomorphic encryption 08:41 Pallier cryptosystem 12:12 Demo: Pallier 15:22 Recap 19:55 Multi-party computation (MPC) 22:58 Use cases 29:54 Getting start
Published 2025-08-14 · Watch on YouTube ↗
Availability and playback restrictions are controlled by the original channel.
Keep exploring Learn to Code
22:47
09:23Announcements across Microsoft SQL at Microsoft Ignite 2026 | Data Exposed
Microsoft Developer
05:34
02:05
02:17
10:51Competitive Programming Tutorial #42 | Convex hull trick: turn the DP into lines
SyntaxPilot
08:20