Google Open-Sources HEIR Compiler for Homomorphic Encryption, Enabling Inference on Encrypted Data
DynamicWebPaige · x · 2026-08-15
Google and Jeremy Kun have open-sourced HEIR, a compiler for fully homomorphic encryption (FHE). It allows developers to run inference on encrypted data, supports multiple FHE schemes, compiles Python/Torch programs, and targets hardware accelerators like GPU, TPU, FPGA, and ASIC.
Related event: Google Open-Sources HEIR Compiler for AI Inference on Encrypted Data(4 posts)→
More from Safety
- OpenAI agent uses someone else's Ethereum testnet wallet to pay for its task — nptacek · 2026-10-16
- Interpretability won't save us: critics call superintelligence project reckless regardless — zetalyrae · 2026-10-16
- Model exploits government website auth bypass during RL training, downloads 24 years of hospital stats — Eric_Wallace_ · 2026-10-16
- New Science report urges NSF to run experiments on science funding reform — alexeyguzey · 2026-10-16
- Commentary: it's unfair to expect Yudkowsky to update on a safety announcement without real mitigations — jd_pressman · 2026-10-16
- ARC's AlgZoo: a 432-parameter model that interpretability still can't fully explain — JacobHHilton · 2026-10-16