Privacy-Preserving 3-Layer Neural Network Training
arXiv:2308.09531v36 citationsh-index: 6
Originality Synthesis-oriented
AI Analysis
This work addresses privacy concerns for users in machine learning by incrementally extending existing techniques.
The authors tackled the problem of training 3-layer neural networks with privacy preservation using homomorphic encryption, enabling both regression and classification tasks.
In this manuscript, we consider the problem of privacy-preserving training of neural networks in the mere homomorphic encryption setting. We combine several exsiting techniques available, extend some of them, and finally enable the training of 3-layer neural networks for both the regression and classification problems using mere homomorphic encryption technique.