Google Open-Sources HEIR, a Compiler Toolchain That Converts Pretrained Models to Run on Encrypted Data
Google Security Blog / Hacker News·high signal
Google announced HEIR (Homomorphic Encryption Intermediate Representation) on August 14, 2026 — an open-source compiler toolchain that converts pretrained AI models to operate directly on homomorphically encrypted inputs, so a server never sees plaintext. Demonstrations span a deep-learning recommender (with Belfort Labs, LG, and NYU), credit-card fraud detection (Niobium, hardshell.ai), Kitsune network intrusion detection, and audio hotword detection. Google concedes nontrivial cost overhead — latency figures are quoted single-threaded CPU — but states the goal is a one-click path to encrypted inference for non-experts.