This is a prototype implementation of NN-EMD framework related to the following papers:
- NN-EMD: Efficiently Training Neural Networks using Encrypted Multi-Sourced Datasets. IEEE TDSC 2021.
- CryptoNN : Training Neural Networks over Encrypted Data. ICDCS 2019.
Note: this implementation of functional encryption cryptosystem is a research prototype and serves primarily as a proof of concept and benchmarking tool for our privacy-preserving neural network training. The code has not been carefully analyzed for potential security flaws, and is not intended for use in production-level code.