nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Data
share
In previous work, Boemer et al. introduced nGraph-HE, an extension to the Intel nGraph deep learning (DL) compiler, that enables data scientists to deploy models with popular frameworks such as TensorFlow and PyTorch with minimal code changes. However, the class of supported models was limited to relatively shallow networks with polynomial activations. Here, we introduce nGraphHE2, which extends nGraph-HE to enable privacy-preserving inference on standard, pre-trained models using their native activation functions and number fields (typically real numbers). The proposed framework leverages the CKKS scheme, whose support for real numbers is friendly to data science, and a client-aided model to compute activation functions. We first present CKKS-specific optimizations, enabling a 3x-88x runtime speedup for scalar encoding, and doubling the throughput through a novel use of CKKS plaintext packing into complex numbers. Second, we optimize ciphertext-plaintext addition and multiplication, yielding 2.6x-4.2x runtime speedup. Third, we present two graph-level optimizations: lazy rescaling and depth-aware encoding. Together, these optimizations enable state-of-the-art throughput of 1,998 images/s on the CryptoNets network. We also present homomorphic evaluation of (to our knowledge) the largest network to date, namely, pre-trained MobileNetV2 models on the ImageNet dataset, with 60.4
READ FULL TEXT