AtHeartEngineer/SHIELD
1
0
Fork 0
mirror of https://github.com/JHUAPL/SHIELD.git synced 2026-01-09 14:48:13 -05:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Vikram Saraph
2025-01-09 11:55:47 -05:00
committed by GitHub
parent 5b55a13332
commit ca05fd01a2
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -1,6 +1,6 @@
# SHIELD: Secure Homomorphic Inference for Encrypted Learning on Data
SHIELD is a library for evalating pre-trained convolutional neural networks on homomorphically encrypted images. It includes code for training models that are suitable for homomorphic evaluation. Implemented neural network operations include convolution, average pooling, GELU, and linear layers.
SHIELD is a library for evaluating pre-trained convolutional neural networks on homomorphically encrypted images. It includes code for training models that are suitable for homomorphic evaluation. Implemented neural network operations include convolution, average pooling, GELU, and linear layers.
This code was used to run the experiments supporting the following paper: [High-Resolution Convolutional Neural Networks on Homomorphically Encrypted Data via Sharding Ciphertexts
](https://arxiv.org/abs/2306.09189). However, operators defined in this project are generic enough to build arbitrary convolutional neural networks as specified in the paper.