The structure and weights of Deep Neural Networks (DNN) typically encode and\ncontain very valuable information about the dataset that was used to train the\nnetwork.\n One way to protect this information when DNN is published is to perform an\ninterference of the network using secure multi-party computations (MPC).\n In this paper, we suggest a translation of deep neural networks to\npolynomials, which are easier to calculate efficiently with MPC techniques.\n We show a way to translate complete networks into a single polynomial and how\nto calculate the polynomial with an efficient and information-secure MPC\nalgorithm.\n The calculation is done without intermediate communication between the\nparticipating parties, which is beneficial in several cases, as explained in\nthe paper.\n