Updates on HEIR, the Homomorphic Encryption Compiler Project
The author provides an update on the HEIR project, a compiler designed to enable homomorphic encryption for machine learning models. The article explains how the tool allows for private inference by processing encrypted data without decryption.
Why it matters
Homomorphic encryption is a foundational technology for privacy-preserving computation, allowing sensitive data to be analyzed securely in the cloud.
On 2026-08-14 I published an article on the Google Security blog with an update on HEIR , our homomorphic encryption (HE) compiler. This is a companion article, in which I have no limits on word count or jargon, and I can feel free to be honest. So strap in.
Assuming you won't read the linked corporate blog post, HEIR is a compiler that converts an input program to a program that operates directly on encrypted data. The guarantee of homomorphic encryption is that, assuming you haven't cracked the cryptography, at no point does the computer running the program get even a single bit of information about the cleartext data used to generate the encrypted inputs. No information about the inputs, outputs, or any intermediate values. 1
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in