Self-learning activation functions to increase accuracy of privacy-preserving Convolutional Neural Networks with homomorphic encryption.

ABSTRACT: The widespread adoption of cloud computing necessitates privacy-preserving techniques that allow information to be processed without disclosure. This paper proposes a method to increase the accuracy and performance of privacy-preserving Convolutional Neural Networks with Homomorphic Encryption (CNN-HE) by Self-Learning Activation Functions (SLAF). SLAFs are polynomials with trainable coefficients updated during training, together with synaptic weights, for each polynomial independently to learn task-specific and CNN-specific features. We theoretically prove its feasibility to approximate any continuous activation function to the desired error as a function of the SLAF degree. Two CNN-HE models are proposed: CNN-HE-SLAF and CNN-HE-SLAF-R. In the first model, all activation functions are rep

SUBMITTER: Pulido-Gaytan B 

PROVIDER: S-EPMC11262700 | biostudies-literature | 2024

REPOSITORIES: biostudies-literature