Search Results for author:
Found 2 papers, 0 papers with code
Optimizing Layerwise Polynomial Approximation for Efficient Private Inference on Fully Homomorphic Encryption: A Dynamic Programming Approach
Unlike the previous works approximating activation functions uniformly and conservatively, this paper presents a \emph{layerwise} degree optimization of activation functions to aggressively reduce the inference time while maintaining classification accuracy by taking into account the characteristics of each layer.
Privacy-Preserving Machine Learning with Fully Homomorphic Encryption for Deep Neural Network
Previous PPML schemes replace non-arithmetic activation functions with simple arithmetic functions instead of adopting approximation methods and do not use bootstrapping, which enables continuous homomorphic evaluations.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
