Compact: Approximating Complex Activation Functions for Secure Computation

arXiv:2309.04664v2 Announce Type: replace
Abstract: Secure multi-party computation (MPC) techniques can be used to provide data privacy when users query deep neural network (DNN) models hosted on a public cloud. State-of-the-art MPC techniques can be directly leveraged for DNN models that use simple activation functions such as ReLU. However, these techniques are ineffective and/or inefficient for the complex and highly non-linear activation functions used in cutting-edge DNN models.
We present Compact, which produces piece-wise polynomial approximations of complex AFs to …

art arxiv can cloud computation cs.cr cs.lg data data privacy functions mpc network neural network party privacy public public cloud query secure computation simple state techniques