Title:
TECHNOLOGY FOR ANALYZING ABNORMAL BEHAVIOR IN DEEP LEARNING-BASED SYSTEM BY USING DATA IMAGING
Document Type and Number:
WIPO Patent Application WO/2019/050108
Kind Code:
A1
Abstract:
The present invention relates to a technology for analyzing abnormal behavior in a deep learning-based system by using data imaging. A method according to the present invention comprises the steps of: receiving data to be analyzed, related to the state of a system to be analyzed; converting, into image data, the inputted data to be analyzed; teaching a neural network unit through the input of the converted image data; and receiving the data to be analyzed, having been converted into the image data, and allowing the neural network unit, having completed learning, to detect or predict abnormal behavior in the system to be analyzed. According to the present invention, abnormal behavior in the system to be analyzed can be classified and recognized through imaging of the data to be analyzed, related to the state of the system to be analyzed, and then through deep learning-based image recognition. Particularly, packet data encrypted with a protocol having unpublicized specifications can be imaged and analyzed without being decrypted. In addition, a multivariate analysis of multi-channel and past information of temporal data sequence are utilized together so as to enable comprehensive classification and prediction.
Inventors:
CHO HONG YEON (KR)
OH TAE YANG (KR)
PARK WON WOO (KR)
OH TAE YANG (KR)
PARK WON WOO (KR)
Application Number:
PCT/KR2018/001841
Publication Date:
March 14, 2019
Filing Date:
February 12, 2018
Export Citation:
Assignee:
CTILAB CO LTD (KR)
International Classes:
G06N3/08; G06V10/764; G06V10/774
Foreign References:
| JP2015026252A | 2015-02-05 | |||
| KR20160148911A | 2016-12-27 | |||
| KR20160074022A | 2016-06-28 | |||
| KR20040093743A | 2004-11-08 | |||
| KR20150013416A | 2015-02-05 |
Attorney, Agent or Firm:
MI PATENT AND LAW FIRM (KR)
Download PDF: