Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Presentation

Private AI: Machine Learning on Encrypted Data

July 6, 2021

Presenters

Kristin Lauter - Facebook AI Research

Description

Abstract: As the world adopts Artificial Intelligence, the privacy risks are many. AI can improve our lives, but may leak our private data. Private AI is based on Homomorphic Encryption (HE), a new encryption paradigm which allows the cloud to operate on private data in encrypted form, without ever decrypting it, enabling private training and private prediction. Our 2016 ICML CryptoNets paper showed for the first time that it was possible to evaluate neural nets on homomorphically encrypted data and opened new research directions combining machine learning and cryptography. The security of Homomorphic Encryption is based on hard problems in mathematics involving lattices, a candidate for post-quantum cryptography. This talk will explain Homomorphic Encryption, Private AI, and explain HE in action.

Presented at

Special Topics on Privacy and Public Auditability (STPPA) series, event #3: July 06, 2021, by video-conference

Event Details

Location

    Virtual event via Webex

Parent Project

See: Privacy-Enhancing Cryptography

Related Topics

Security and Privacy: cryptography, privacy

Created July 08, 2021, Updated October 08, 2021