Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
EVALUATION DEVICE, EVALUATION METHOD, AND EVALUATION PROGRAM
Document Type and Number:
WIPO Patent Application WO/2020/195826
Kind Code:
A1
Abstract:
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.

Inventors:
TAKAHASHI TOMOKATSU (JP)
YAMADA MASANORI (JP)
Application Number:
PCT/JP2020/010520
Publication Date:
October 01, 2020
Filing Date:
March 11, 2020
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
NIPPON TELEGRAPH & TELEPHONE (JP)
International Classes:
G06N3/02
Other References:
KOS, JERNEJ ET AL., ADVERSARIAL EXAMPLES FOR GENERATIVE MODELS , ARXIV, 22 February 2017 (2017-02-22), pages 5 - 7, XP033379530, Retrieved from the Internet [retrieved on 20200525]
PELLEG, DAN ET AL.: "X-means: Extending K-means with Efficient Estimation of the Number of Clusters", PROC. OF THE 17TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING, 2000, pages 727 - 734, XP55742951
LOSALKA, ARPAN: "Resisting Adversarial Attacks Using Gaussian Mixture Variational Autoencoders", TOWARDS DATA SCIENCE, 18 February 2019 (2019-02-18), XP55742953, Retrieved from the Internet [retrieved on 20200525]
VARIATIONAL AUTO ENCODER (VAE, 7 March 2019 (2019-03-07), Retrieved from the Internet
ATTACK ON SUPERVISED LEARNING, 7 March 2019 (2019-03-07)
ATTACK ON UNSUPERVISED LEARNING, 7 March 2019 (2019-03-07)
See also references of EP 3929818A4
Attorney, Agent or Firm:
SAKAI INTERNATIONAL PATENT OFFICE (JP)
Download PDF: