Title:
METHOD FOR TRAINING AND TESTING OBFUSCATION NETWORK CAPABLE OF PROCESSING DATA TO BE CONCEALED FOR PRIVACY, AND TRAINING DEVICE AND TESTING DEVICE USING THE SAME
Document Type and Number:
WIPO Patent Application WO/2020/022704
Kind Code:
A1
Abstract:
A method for learning an obfuscation network used for concealing original data is provided. The method includes steps of: a learning device instructing the obfuscation network to obfuscate inputted training data, inputting the obfuscated training data into a learning network, and allowing the learning network to apply a network operation to the obfuscated training data and thus to generate 1-st characteristic information, and allowing the learning network to apply a network operation to the inputted training data and thus to generate 2-nd characteristic information, and learning the obfuscation network such that an error is minimized, calculated by referring to part of an error acquired by referring to the 1-st and the 2-nd characteristic information, and an error acquired by referring to a task specific output and its corresponding ground truth, and such that an error is maximized, calculated by referring to the training data and the obfuscated training data.
More Like This:
Inventors:
KIM TAE HOON (KR)
Application Number:
PCT/KR2019/008939
Publication Date:
January 30, 2020
Filing Date:
July 19, 2019
Export Citation:
Assignee:
DEEPING SOURCE INC (KR)
International Classes:
G06F21/62; G06F16/35; G06N3/08; G06N20/00; G06T3/00
Foreign References:
| US20170317983A1 | 2017-11-02 | |||
| US20180165597A1 | 2018-06-14 | |||
| US20170243028A1 | 2017-08-24 | |||
| JP2018106216A | 2018-07-05 | |||
| KR101861520B1 | 2018-05-28 | |||
| US20140328547A1 | 2014-11-06 |
Other References:
HUI XU ET AL.: "DeepObfuscation: Securing the Structure of Convolutional Neural Networks via Knowledge Distillation", ARXIV:1806.10313V1, 27 June 2018 (2018-06-27), pages 1 - 14, XP080894997, Retrieved from the Internet [retrieved on 20191017]
JACOB CONRAD TRINIDAD: "Reconstructing Obfuscated Human Faces", THESIS, 8 January 2017 (2017-01-08), pages 1 - 8, XP055681748, Retrieved from the Internet [retrieved on 20191017]
NIKHIL CHHABRA: "Generative Adversarial Networks for Image Anonymization", MASTER THESIS, 17 October 2019 (2019-10-17), Aachen, Germany, pages 1 - 59, XP055681759, Retrieved from the Internet
JOURABLOO AMIN ET AL.: "Attribute preserved face de-identification", INT. CONF. ON BIOMETRICS (ICB), IEEE, 19 May 2015 (2015-05-19), pages 278 - 285, XP033166158, DOI: 10.1109/ICB.2015.7139096
MEDEN BLAZ ET AL.: "IET Sign. Proc", vol. 11, 1 December 2017, THE INSTITUTION OF ENGINEERING AND TECHNOLOG, article "Face deidentification with generative deep neural networks", pages: 1046 - 1054
See also references of EP 3827366A4
JACOB CONRAD TRINIDAD: "Reconstructing Obfuscated Human Faces", THESIS, 8 January 2017 (2017-01-08), pages 1 - 8, XP055681748, Retrieved from the Internet
NIKHIL CHHABRA: "Generative Adversarial Networks for Image Anonymization", MASTER THESIS, 17 October 2019 (2019-10-17), Aachen, Germany, pages 1 - 59, XP055681759, Retrieved from the Internet
JOURABLOO AMIN ET AL.: "Attribute preserved face de-identification", INT. CONF. ON BIOMETRICS (ICB), IEEE, 19 May 2015 (2015-05-19), pages 278 - 285, XP033166158, DOI: 10.1109/ICB.2015.7139096
MEDEN BLAZ ET AL.: "IET Sign. Proc", vol. 11, 1 December 2017, THE INSTITUTION OF ENGINEERING AND TECHNOLOG, article "Face deidentification with generative deep neural networks", pages: 1046 - 1054
See also references of EP 3827366A4
Attorney, Agent or Firm:
SU INTELLECTUAL PROPERTY (KR)
Download PDF: