How Google is Making Private AI Practical with Homomorphic Encryption
Aug 14, 2026 — Jeremy Kun, Staff Software Engineer, Google
Today we’re excited to showcase HEIR, the latest powerful tool added to our Private Computing Toolkit. HEIR is an open source compiler that unlocks cryptographically-secure private AI inference.
Homomorphic encryption context
Homomorphic encryption allows computations on encrypted data without decrypting inputs on the server. Servers process ciphertexts and return encrypted results. This shifts the capability/privacy trade-off to a question of cost, and that cost is rapidly decreasing.
Manually converting programs to use homomorphic encryption efficiently has historically required teams of cryptographers.
About HEIR
HEIR (Homomorphic Encryption Intermediate Representation) is an open-source compiler toolchain and development platform for homomorphic encryption. HEIR can convert pre-trained AI models that operate on unencrypted data to operate on encrypted inputs. Google’s vision is to make HEIR a one-click solution for non-experts to incorporate encrypted inference into production applications.
Since announcing intentions in 2023, Google has partnered with hardware accelerator companies including Belfort, Niobium, Cornami, and Optalysys. HEIR has become a research platform with collaborations at Georgia Tech, Carnegie Mellon, UC Santa Barbara, Illinois Institute of Technology, Purdue, University of Edinburgh, Tsinghua University, and others. Four peer-reviewed publications built on HEIR to date.
Demo applications (single-threaded CPU latency)
All compiled with HEIR; source code on GitHub:
- Deep Learning Recommendation Model — private content recommendations without seeing user features (with Belfort Labs, LG, NYU)
- Credit card fraud detection — with Niobium and hardshell.ai
- Threat intrusion (Kitsune) — anomaly detection on encrypted network traffic without revealing packet contents (with Niobium)
- Hotword detector — recognize hotwords while protecting audio privacy (with Belfort Labs)
Google plans to demonstrate latency benefits of hardware accelerators in the near future.