papers
Publications (19)
cs.CR2025
Volley Revolver: A Novel Matrix-Encoding Method for Privacy-Preserving Deep Learning (Inference++)
John Chiang
cs.CR2026
LibFHE: A Numba-Based CUDA-Python Library for Non-RNS CKKS-BGV Fully Homomorphic Encryption on GPUs
John Chiang
cs.LG2022
On Polynomial Approximation of Activation Function
John Chiang
cs.CR2026
Privacy-Preserving Logistic Regression Training with A Faster Gradient Variant
John Chiang
The paper proposes a quadratic gradient method to improve privacy-preserving logistic regression training, enhancing NAG, AdaGrad, and Adam and achieving fast convergence even unde…
#privacy-preserving machine learning#logistic regression#homomorphic encryption#gradient optimization
cs.CR2025
Privacy-Preserving CNN Training with Transfer Learning: Two Hidden Layers
John Chiang
cs.LG2024
LFFR: Logistic Function For (single-output) Regression
John Chiang
cs.CR2026
Trimming: Decoupling Multiplicative Depth from Modulus Chains in RNS-CKKS via Rational Levels
John Chiang
cs.CR2025
CryptoUNets: Applying Convolutional Networks to Encrypted Data for Biomedical Image Segmentation
John Chiang
cs.CR2024
LFFR: Logistic Function For (multi-output) Regression
John Chiang
cs.CR2025
Privacy-Preserving Logistic Regression Training on Large Datasets
John Chiang
cs.CR2026
Volley Revolver: A Novel Matrix-Encoding Method for Privacy-Preserving Neural Networks (Inference)
John Chiang
cs.CR2025
Privacy-Preserving 3-Layer Neural Network Training
John Chiang
math.OC2026
Quasi-Quadratic Gradient: A New Direction for Accelerating the BFGS Method in Quasi-Newton Optimization
John Chiang
cs.LG2023
Activation Functions Not To Active: A Plausible Theory on Interpreting Neural Networks
John Chiang
math.OC2026
Generalized Quadratic Gradient: A New Direction in Optimization via the Fusion of Positive-Definite Curvature Matrices and Gradients into A Unified Framework
John Chiang
cs.CR2025
Privacy-Preserving CNN Training with Transfer Learning: Multiclass Logistic Regression
John Chiang
math.OC2026
Simplified Quadratic Gradient: A Unified Framework Bridging Gradient Descent and Newton-Type Methods by Synthesizing Hessians and Gradients
John Chiang
cs.LG2023
Multinomial Logistic Regression Algorithms via Quadratic Gradient
John Chiang
cs.CR2024
A Simple Solution for Homomorphic Evaluation on Large Intervals
John Chiang