NeuJeans: Private Neural Network Inference with Joint Optimization of Convolution and Bootstrapping

no code implementations • 7 Dec 2023 • Jae Hyung Ju, Jaiyoung Park, Jongmin Kim, Donghwan Kim, Jung Ho Ahn

NeuJeans accelerates the performance of conv2d by up to 5. 68 times compared to state-of-the-art FHE-based PI work and performs the PI of a CNN at the scale of ImageNet (ResNet18) within a mere few seconds

HyPHEN: A Hybrid Packing Method and Optimizations for Homomorphic Encryption-Based Neural Networks

no code implementations • 5 Feb 2023 • Donghwan Kim, Jaiyoung Park, Jongmin Kim, Sangpyo Kim, Jung Ho Ahn

Convolutional neural network (CNN) inference using fully homomorphic encryption (FHE) is a promising private inference (PI) solution due to the capability of FHE that enables offloading the whole computation process to the server while protecting the privacy of sensitive user data.

AESPA: Accuracy Preserving Low-degree Polynomial Activation for Fast Private Inference

no code implementations • 18 Jan 2022 • Jaiyoung Park, Michael Jaemin Kim, Wonkyung Jung, Jung Ho Ahn

We apply AESPA to popular ML models, such as VGGNet, ResNet, and pre-activation ResNet, to show an inference accuracy comparable to those of the standard models with ReLU activation, achieving superior accuracy over prior low-degree polynomial studies.

Accelerating Number Theoretic Transformations for Bootstrappable Homomorphic Encryption on GPUs

no code implementations • 3 Dec 2020 • Sangpyo Kim, Wonkyung Jung, Jaiyoung Park, Jung Ho Ahn

Homomorphic encryption (HE) draws huge attention as it provides a way of privacy-preserving computations on encrypted messages.

Cryptography and Security Distributed, Parallel, and Cluster Computing

Restructuring Batch Normalization to Accelerate CNN Training

1 code implementation • 4 Jul 2018 • Wonkyung Jung, Daejin Jung, and Byeongho Kim, Sunjung Lee, Wonjong Rhee, Jung Ho Ahn

Batch Normalization (BN) has become a core design block of modern Convolutional Neural Networks (CNNs).