Information processing system, inference method, attack detection method, inference execution program and attack detection program

Abstract

To provide a robust information processing system against attacks by Adversarial Example. A neural network model, a latent space databasefor storing position information in a latent space in which first output vectors, which are output vectors of a predetermined hidden layer included in the neural network model, are embedded concerning input data used for learning of the neural network model, and an inference control unitfor making an inference using the neural network model and the latent space database are provided. The inference control unit infers the input data based on the positional relationship between the second output vector, which is an output vector of the predetermined hidden layer concerning input data to be inferred, and the first output vectors in said latent space.