Deep Neural Networks for Encrypted Inference with TFHE
This work addresses privacy-preserving machine learning for sensitive data like health or biometrics, but it is incremental as it adapts existing DNNs to FHE constraints.
The authors tackled the problem of performing deep neural network inference on encrypted data using fully homomorphic encryption (FHE), specifically with TFHE, and demonstrated architectures for computer vision tasks benchmarked with the Concrete stack.
Fully homomorphic encryption (FHE) is an encryption method that allows to perform computation on encrypted data, without decryption. FHE preserves the privacy of the users of online services that handle sensitive data, such as health data, biometrics, credit scores and other personal information. A common way to provide a valuable service on such data is through machine learning and, at this time, Neural Networks are the dominant machine learning model for unstructured data. In this work we show how to construct Deep Neural Networks (DNN) that are compatible with the constraints of TFHE, an FHE scheme that allows arbitrary depth computation circuits. We discuss the constraints and show the architecture of DNNs for two computer vision tasks. We benchmark the architectures using the Concrete stack, an open-source implementation of TFHE.