Google’s open-source HEIR lets AI work with data it can’t see
Google open-sourced HEIR, a compiler toolchain that converts pre-trained AI models to operate on homomorphically encrypted data without exposing it.
Google's HEIR (Homomorphic Encryption Intermediate Representation) is an open-source compiler toolchain and development platform for fully homomorphic encryption, announced in 2023 and now supporting four peer-reviewed publications. It compiles Python programs handling sensitive data into implementations that process encrypted inputs, supporting multiple FHE schemes, libraries, front-end languages, and hardware accelerators such as GPUs, TPUs, FPGAs, and custom ASICs. Demonstrated applications include private recommendations, credit card fraud detection, network intrusion detection, and hotword recognition.
- Converts models built for plaintext data into encrypted-input processing
- Supports multiple FHE schemes, libraries, and front-end programming languages
- Targets code generation for GPU, TPU, FPGA, and ASIC accelerators
- Demonstrated in fraud detection, intrusion detection, and private recommendations
From the original article
1 min read at helpnetsecurity.com
Google’s researchers and engineers developed the Homomorphic Encryption Intermediate Representation (HEIR) compiler project, an open-source compiler toolchain and development platform for homomorphic encryption. It can convert pre-trained AI models designed to operate on unencrypted data into models that process encrypted inputs.
By @helpnetsecurity · helpnetsecurity.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.