AutoFHE: Automated Adaption of CNNs for Efficient Evaluation over FHE

ePrint Report: AutoFHE: Automated Adaption of CNNs for Efficient Evaluation over FHE

Wei Ao, Vishnu Boddeti

Secure inference of deep convolutional neural networks (CNNs) was recently demonstrated under RNS-CKKS. The state-of-the-art solution uses a high-order composite polynomial to approximate all ReLUs. However, it results in prohibitively high latency because bootstrapping is required to refresh zero-level ciphertext after every Conv-BN layer. To accelerate inference of CNNs over FHE and automatically design homomorphic evaluation architectures of CNNs, we propose AutoFHE: a bi-level …

art automated ciphertext cnns design eprint report evaluation fhe high latency networks neural networks order report results solution state under