
The author presents optimized protocols for implementing nonlinear activation functions in a secure two-party setting, focusing on exponential, sigmoid, and Tanh functions. These protocols aim to achieve state-of-the-art precision while reducing runtime significantly.


coremsg

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


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


title_rewrite


개인 정보 보호를 위한 비선형 활성화 함수에 대한 최적화된 안전한 이중 계산 프로토콜을 제안합니다.


opaf-optimized-secure-two-party-computation-protocols-for-nonlinear-activation-functions-in-recurrent-neural-network


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