CHET: Compiler and Runtime for Homomorphic Evaluation of Tensor Programs

By Roshan Dathathri, Olli Saarikivi, Hao Chen, Kim Laine, Kristin E. Lauter, Saeed Maleki, M. Musuvathi, Todd Mytkowicz. 2018

14 citations recorded by the source corpus.

Fully Homomorphic Encryption (FHE) refers to a set of encryption schemes that allow computations to be applied directly on encrypted data without requiring a secret key. This enables novel application scenarios where a client can safely offload storage and computation to a third-party cloud provider without having to trust the software and the hardware vendors with the decryption keys. Recent advances in both FHE schemes and implementations have moved such applications from theoretical possibilities into the realm of practicalities. This paper proposes a compact and well-reasoned interface called the Homomorphic Instruction Set Architecture (HISA) for developing FHE applications. Just as the hardware ISA interface enabled hardware advances to proceed independent of software advances in the compiler and language runtimes, HISA decouples compiler optimizations and runtimes for supporting FHE applications from advancements in the underlying FHE schemes. This paper demonstrates the capabilities of HISA by building an end-to-end software stack for evaluating neural network models on encrypted data. Our stack includes an end-to-end compiler, runtime, and a set of optimizations. Our approach shows generated code, on a set of popular neural network architectures, is faster than hand-optimized implementations.

Subfields: Artificial Intelligence, Hardware and Architecture

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Kim Laine
2. Blake Pelton
3. M. Sadegh Riazi
4. Wei Dai
5. Berk Sunar

In Hardware and Architecture

1. Blake Pelton
2. M. Sadegh Riazi
3. Wei Dai
4. Kim Laine

Citations in the corpus

• HEAX: An Architecture for Computing on Encrypted Data (2019, methodology): “For instance, in the context of Machine Learning as a Service (MLaaS), FHE can be used to perform oblivious neural network inference [25, 35]: clients send the encrypted version of their data, the cloud server runs ML models on the encrypted queries, and returns the result to the clients.”