Privacy-Preserving Machine Learning with Fully Homomorphic Encryption

Channel:
United States Google TechTalks
Subscribers:
348,000
Published on ● Video Link: https://www.youtube.com/watch?v=-lhn2GdHhGc


Duration: 42:45
1,973 views
34

A Google TechTalk, presented by Jordan Fréry, 2023-01-17
ABSTRACT: In today's digital age, protecting privacy has become increasingly difficult. However, new developments such as Fully Homomorphic Encryption (FHE) provide a means of safeguarding sensitive client information. We are excited to present Concrete-ML, our open-source library that allows for the seamless conversion of Machine Learning (ML) models into their FHE counterparts. With our technology, clients can enjoy zero-trust interactions with service providers while also enabling the deployment of ML models on untrusted servers without compromising the privacy of user data.

Jordan Fréry is a research scientist at Zama



Other Videos By Google TechTalks


2023-03-07Zürich Go Meetup: Let’s Build a Game with Go
2023-03-07Zürich Go Meetup: Run Go programs on your Raspberry Pi with gokrazy!
2023-03-03Online Covering: Secretaries, Prophets and Universal Maps
2023-03-03Auto-bidding in Online Advertising: Campaign Management and Fairness
2023-03-03Tree Learning: Optimal Algorithms and Sample Complexity
2023-03-03A Fast Algorithm for Adaptive Private Mean Estimation
2023-02-13Piers Ridyard | CEO RDX Works | Radix Protocol | web3 talks | Dec 7th 2022 | MC: Blake DeBenon
2023-02-10Sergey Gorbunov | Co-Founder Axelar | web3 talks | Jan 26th 2023 | MC: Marlon Ruiz
2023-02-10Fast Neural Kernel Embeddings for General Activations
2023-02-10Pathwise Conditioning and Non-Euclidean Gaussian Processes
2023-02-10Privacy-Preserving Machine Learning with Fully Homomorphic Encryption
2023-01-19Charles Hoskinson | CEO of Input Output Global | web3 talks | Jan 5th 2023 | MC: Marlon Ruiz
2023-01-18Control, Confidentiality, and the Right to be Forgotten
2023-01-18The Saddle Point Accountant for Differential Privacy
2023-01-18Analog vs. Digital Epsilons: Implementation Considerations Considerations for Differential Privacy
2023-01-18Secure Self-supervised Learning
2023-01-18Example Memorization in Learning: Batch and Streaming
2023-01-18Marginal-based Methods for Differentially Private Synthetic Data
2023-01-18Private Convex Optimization via Exponential Mechanism
2023-01-18Differentially Private Multi-party Data Release for Linear Regression
2023-01-18On Privacy Implications of Machine Unlearning