OPAF: Optimized Secure Two-Party Computation Protocols for Nonlinear Activation Functions in Recurrent Neural Network

arXiv:2403.00239v1 Announce Type: new
Abstract: Deep neural network (DNN) typically involves convolutions, pooling, and activation function. Due to the growing concern about privacy, privacy-preserving DNN becomes a hot research topic. Generally, the convolution and pooling operations can be supported by additive homomorphic and secure comparison, but the secure implementation of activation functions is not so straightforward for the requirements of accuracy and efficiency, especially for the non-linear ones such as exponential, sigmoid, and tanh functions. This paper pays a special …

arxiv can computation cs.cr function functions hot network neural network operations party privacy protocols research topic