EVALUATION DEVICE, EVALUATION METHOD, AND EVALUATION PROGRAM

• Main Authors: TAKAHASHI TOMOKATSU, YAMADA MASANORI
• Format: Patent
• Language: Chinese; English
• Published: 22.10.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

An evaluation device of the present invention receives input of latent variables of a variational auto-encoder, clusters the latent variables that were input, and for each cluster, assigns a label indicating the cluster to the latent variables belonging to the cluster. Afterwards, the evaluation device implements learning of a classifier such that the latent variables are accurately classified on the basis of the assigned label, subjects the classifier after learning to an evaluation of resistance to an adversarial attack, and outputs the results of the resistance evaluation. Through this, the evaluation device can evaluate the resistance to an adversarial attack even with a variational auto-encoder that uses, as input data, data without a label. 评价装置接受变分自编码器的隐变量的输入，对所输入的隐变量进行聚类，按每个聚类对属于该聚类的隐变量赋予表示上述聚类的标签。然后，评价装置进行分类器的学习，以按照所赋予的标签正确地对隐变量进行分类，对学习后的分类器进行Adversarial Attack的耐性评价，输出耐性评价的结果。由此，评价装置即使是使用无标签数据作为输入数据的变分自编码器，也能够进行Adversarial Attack的耐性评价。