Google · Google Blog
Google is making private AI practical with homomorphic encryption
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
Today they're excited to showcase HEIR, the latest powerful tool added to their Private Computing Toolkit.
Key facts
- Since announcing their intentions in 2023, they've seen the homomorphic encryption community embrace HEIR — This has resulted in collaborations with Georgia Tech, Carnegie Mellon, UC Santa Barbara, Illinois Institute of Technology, Purdue, the University of Edinburgh, Tsinghua University, and others
- Today they're excited to showcase HEIR, the latest powerful tool added to their Private Computing Toolkit
- HEIR (Homomorphic Encryption Intermediate Representation) is an open-source compiler toolchain and development platform for homomorphic encryption
Summary
As new benefits emerge with the growth of AI, balancing privacy and security is top of mind. Alternative mechanisms to provide the same features, like local processing, are limited by the capabilities of the local device and the sensitivity of the service provider's IP. A solution to these issues is homomorphic encryption, a rapidly maturing technology that fundamentally alters this trade-off by allowing computations to be performed directly on encrypted data. Servers can process ciphertexts and return encrypted results without exposing any underlying information. Google’s history of innovations in privacy technology—from differential privacy and private set membership to private information retrieval and secure enclaves on Google Cloud —has always focused on securing user data. To overcome the usability challenges and advance the opportunity homomorphic encryption provides, researchers and engineers at Google built the HEIR compiler project.