5 papers
Trimming: Decoupling Multiplicative Depth from Modulus Chains in RNS-CKKS via Rational Levels
John Chiang
Recent work on Grafting decouples scale factors from ciphertext moduli, enabling more flexible precision management in RNS-CKKS. However, the multiplicative depth remains fundament…
LibFHE: A Numba-Based CUDA-Python Library for Non-RNS CKKS-BGV Fully Homomorphic Encryption on GPUs
John Chiang
It has been a decade since the fourth-generation FHE framework, CKKS, was proposed; yet, there is still no indicator pointing toward a fifth-generation successor; and in recent yea…
Volley Revolver: A Novel Matrix-Encoding Method for Privacy-Preserving Deep Learning (Inference++)
John Chiang
Privacy-preserving inference of convolutional neural networks (CNNs) using homomorphic encryption has emerged as a promising approach for enabling secure machine learning in untrus…
CryptoUNets: Applying Convolutional Networks to Encrypted Data for Biomedical Image Segmentation
John Chiang
In this manuscript, we demonstrate the feasibility of a privacy-preserving U-Net deep learning inference framework, namely, homomorphic encryption-based U-Net inference. That is, U…
Privacy-Preserving CNN Training with Transfer Learning: Two Hidden Layers
John Chiang
In this paper, we present the demonstration of training a four-layer neural network entirely using fully homomorphic encryption (FHE), supporting both single-output and multi-outpu…