-
NN-EMD: Efficiently Training Neural Networks using Encrypted Multi-sourced Da...
Training complex neural network models using third-party cloud-based infrastructure among multiple data sources is a promising approach among existing machine learning... -
pvCNN: Privacy-Preserving and Verifiable Convolutional Neural Network Testing
We propose a new approach for privacy-preserving and verifiable convolutional neural network (CNN) testing in a distrustful multi-stakeholder environment. -
XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learning
User-generated data distributions are often imbalanced across devices and labels, hampering the performance of federated learning (FL). To remedy to this non-independent and... -
Efficient Privacy Preserving Edge Computing Framework for Image Classification
The proposed framework is for image classification in edge computing systems. It uses autoencoders to extract critical features from the data and then trains a classifier on the... -
Privacy-Preserving Image Classification Using Vision Transformer
Privacy-preserving image classification method that uses ViT and a block-wise encryption method
