CryptoUNets: Applying Convolutional Networks to Encrypted Data for Biomedical Image Segmentation
By: John Chiang
Potential Business Impact:
Lets computers analyze private pictures safely.
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-Net inference can be performed solely using homomorphic encryption techniques. To our knowledge, this is the first work to achieve support perform implement enable U-Net inference entirely based on homomorphic encryption ?. The primary technical challenge lies in data encoding. To address this, we employ a flexible encoding scheme, termed Double Volley Revolver, which enables effective support for skip connections and upsampling operations within the U-Net architecture. We adopt a tailored HE-friendly U-Net design incorporating square activation functions, mean pooling layers, and transposed convolution layers (implemented as ConvTranspose2d in PyTorch) with a kernel size of 2 and stride of 2. After training the model in plaintext, we deploy the resulting parameters using the HEAAN homomorphic encryption library to perform encrypted U-Net inference.
Similar Papers
Privacy-Preserving Chest X-ray Classification in Latent Space with Homomorphically Encrypted Neural Inference
Image and Video Processing
Lets doctors analyze private X-rays safely.
Privacy-Preserving CNN Training with Transfer Learning: Two Hidden Layers
Cryptography and Security
Trains computers on secret data without seeing it.
PrivSpike: Employing Homomorphic Encryption for Private Inference of Deep Spiking Neural Networks
Cryptography and Security
Keeps private data safe during computer learning.