Method for verifying convolutional neural network model and device thereof

A non-transitory computer readable recording medium product recording program codes for performing a method for verifying a convolutional neural network model comprising the steps of:

• (a) generating a polynomial circuit equation for a first configuration of a plurality of configurations configuring the convolutional neural network model;
• (b) generating a first commitment value and a first proof value by applying a zero-knowledge proof scheme based on the polynomial circuit equation;
• (c) generating an arithmetic circuit equation for a second configuration of the plurality of configurations;
• (d) generating a second commitment value and a second proof value by applying a zero-knowledge proof scheme based on the arithmetic circuit equation;
• and
• (e) generating a connection proof value connecting the first commitment value and the second commitment value.

A device for verifying a convolutional neural network model comprising:

• a memory for storing at least one instruction;
• and
• a processor for executing the instructions stored in the memory,
• wherein the instructions perform the steps of:
• (a) generating a polynomial circuit equation for a convolution operation configuring the convolutional neural network model;
• (b) generating a first commitment value and a first proof value by applying a zero-knowledge proof scheme based on the polynomial circuit equation;
• (c) generating an arithmetic circuit equation for other operations except for the convolution operation configuring the convolutional neural network model;
• (d) generating a second commitment value and a second proof value by applying a zero-knowledge proof scheme based on the arithmetic circuit equation;
• and
• (e) generating a connection proof value connecting the first commitment value and the second commitment value.