Some content of this application is unavailable at the moment.
If this situation persist, please contact us atFeedback&Contact
1. (WO2019050108) TECHNOLOGY FOR ANALYZING ABNORMAL BEHAVIOR IN DEEP LEARNING-BASED SYSTEM BY USING DATA IMAGING
Latest bibliographic data on file with the International Bureau    Submit observation

Pub. No.: WO/2019/050108 International Application No.: PCT/KR2018/001841
Publication Date: 14.03.2019 International Filing Date: 12.02.2018
IPC:
G06K 9/62 (2006.01) ,G06N 3/08 (2006.01)
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
K
RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9
Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62
Methods or arrangements for recognition using electronic means
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3
Computer systems based on biological models
02
using neural network models
08
Learning methods
Applicants:
주식회사 씨티아이랩 CTILAB CO., LTD. [KR/KR]; 서울시 서초구 태봉로 114, 6층 601호 #601, 6F., 114, Taebong-ro Seocho-gu Seoul 06764, KR
Inventors:
조홍연 CHO, Hong Yeon; KR
오태양 OH, Tae Yang; KR
박원우 PARK, Won Woo; KR
Agent:
특허법인 명인 MI PATENT AND LAW FIRM; 서울시 강남구 테헤란로 4길 45, 5층 5F., 45 Teheran-ro 4-gil Gangnam-gu Seoul 06240, KR
Priority Data:
10-2017-011405406.09.2017KR
Title (EN) TECHNOLOGY FOR ANALYZING ABNORMAL BEHAVIOR IN DEEP LEARNING-BASED SYSTEM BY USING DATA IMAGING
(FR) TECHNOLOGIE POUR ANALYSER UN COMPORTEMENT ANORMAL DANS UN SYSTÈME BASÉ SUR UN APPRENTISSAGE PROFOND EN UTILISANT UNE IMAGERIE DE DONNÉES
(KO) 데이터 이미지화를 이용한 딥러닝 기반 시스템 이상행위 분석 기술
Abstract:
(EN) 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.
(FR) La présente invention concerne une technologie pour analyser un comportement anormal dans un système basé sur un apprentissage profond à l'aide d'une imagerie de données. Un procédé selon la présente invention comprend les étapes consistant à : recevoir des données à analyser, associées à l'état d'un système à analyser ; convertir, en données d'image, les données entrées à analyser ; entraîner une unité de réseau neuronal par l'entrée des données d'image converties ; et recevoir des données à analyser, converties en données d'image, et permettre à l'unité de réseau neuronal, ayant effectué un apprentissage, de détecter ou de prédire un comportement anormal dans le système à analyser. Selon la présente invention, un comportement anormal dans le système à analyser peut être classé et reconnu par imagerie des données à analyser, en rapport avec l'état du système à analyser, puis par une reconnaissance d'image basée sur un apprentissage profond. En particulier, des données par paquets cryptées avec un protocole ayant des spécifications non publiquement peuvent être imagées et analysées sans être décryptées. De plus, une analyse à variables multiples de multiples canaux et des informations passées de séquence de données temporelles sont utilisées ensemble de manière à permettre une classification et une prédiction complètes.
(KO) 본 발명은 데이터 이미지화를 이용한 딥러닝 기반 시스템 이상행위 분석 기술에 관한 것이다. 본 발명에 따른 방법은 분석 대상 시스템의 상태와 관련된 분석 대상 데이터를 입력받는 단계, 입력된 분석 대상 데이터를 이미지 데이터로 변환하는 단계, 변환된 이미지 데이터를 입력으로 신경망부를 학습시키는 단계, 그리고 이미지 데이터로 변환된 분석 대상 데이터를 입력받아 학습이 완료된 신경망부에서 분석 대상 시스템의 이상 행위를 검출하거나 예측하는 단계를 포함한다. 본 발명에 의하면 분석 대상 시스템의 상태와 관련된 분석 대상 데이터를 이미지화한 후 딥러닝 기반의 이미지 인식을 통해 분석 대상 시스템에서의 이상행위를 분류 및 인식할 수 있다. 특히 스펙이 공개되지 않은 프로토콜로 암호화된 패킷 데이터에 대해서도 해독하지 않고 이미지화하여 분석할 수 있다. 또한 다중 채널의 다변량 분석과 시간적인 데이터 시퀀스의 과거 정보를 함께 활용하여 종합적인 분류 및 예측이 가능하다.
front page image
Designated States: AE, AG, AL, AM, AO, AT, AU, AZ, BA, BB, BG, BH, BN, BR, BW, BY, BZ, CA, CH, CL, CN, CO, CR, CU, CZ, DE, DJ, DK, DM, DO, DZ, EC, EE, EG, ES, FI, GB, GD, GE, GH, GM, GT, HN, HR, HU, ID, IL, IN, IR, IS, JO, JP, KE, KG, KH, KN, KP, KW, KZ, LA, LC, LK, LR, LS, LU, LY, MA, MD, ME, MG, MK, MN, MW, MX, MY, MZ, NA, NG, NI, NO, NZ, OM, PA, PE, PG, PH, PL, PT, QA, RO, RS, RU, RW, SA, SC, SD, SE, SG, SK, SL, SM, ST, SV, SY, TH, TJ, TM, TN, TR, TT, TZ, UA, UG, US, UZ, VC, VN, ZA, ZM, ZW
African Regional Intellectual Property Organization (ARIPO) (BW, GH, GM, KE, LR, LS, MW, MZ, NA, RW, SD, SL, ST, SZ, TZ, UG, ZM, ZW)
Eurasian Patent Office (AM, AZ, BY, KG, KZ, RU, TJ, TM)
European Patent Office (EPO) (AL, AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI, FR, GB, GR, HR, HU, IE, IS, IT, LT, LU, LV, MC, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, SM, TR)
African Intellectual Property Organization (BF, BJ, CF, CG, CI, CM, GA, GN, GQ, GW, KM, ML, MR, NE, SN, TD, TG)
Publication Language: Korean (KO)
Filing Language: Korean (KO)