METHOD AND APPARATUS FOR DETECTING ATTACK IN NETWORK

The present invention relates to a method and apparatus for detecting an attack coming from the outside in a network formed of IoT equipment and, more specifically, to a method and apparatus for detecting an external attack by using traffic data collected from an IoT network. According to one embodi...

Full description

Saved in:
Bibliographic Details
Main Authors CHUN SE LIN, KWON TAE KYOUNG
Format Patent
LanguageEnglish
Korean
Published 31.05.2022
Subjects
Online AccessGet full text

Cover

Loading…
Abstract The present invention relates to a method and apparatus for detecting an attack coming from the outside in a network formed of IoT equipment and, more specifically, to a method and apparatus for detecting an external attack by using traffic data collected from an IoT network. According to one embodiment of the present invention, the method comprises the following steps of: collecting traffic data packets for an IoT network; processing the traffic data packets to extract feature vectors; and executing an attack detection model to detect whether there is an attack on the IoT network corresponding to the feature vector. Before the collection step, the method includes a step of generating the attack detection model. The attack detection model generation step includes a step of using the feature vector, as a result of processing traffic data packets in a steady state collected from the IoT network, as an input to train an unsupervised learning-based deep neural network model and a step of using the feature vector as an input through training of the deep neural network to complete and store the attack detection model detecting an attack in the IoT network. 본 발명은 IoT 장비로 구성된 네트워크에서 외부로부터 들어오는 공격을 탐지하기 위한 방법 및 장치에 관한 것으로서, IoT 네트워크에서 수집된 트래픽 데이터를 활용하여 외부로부터의 공격을 탐지하는 방법 및 장치에 관한 것이다. 본 발명의 일 실시 예에 따른 네트워크 공격 탐지 방법은, IoT 네트워크에 대한 트래픽 데이터 패킷을 수집하는 단계와, 트래픽 데이터 패킷을 가공하여 특성 벡터를 추출하는 단계와, 공격 탐지 모델을 실행하여 특성 벡터에 대응하는 IoT 네트워크에 대한 공격 여부를 탐지하는 단계를 포함하고, 수집하는 단계 이전에, 공격 탐지 모델을 생성하는 단계를 더 포함하고, 공격 탐지 모델을 생성하는 단계는, IoT 네트워크로부터 수집한 정상 상태의 트래픽 데이터 패킷에 대한 가공 결과로서의 특성 벡터를 입력으로 하여 비지도 학습 기반의 심층신경망 모델을 훈련시키는 단계와, 심층신경망의 훈련을 통하여, 특성 벡터를 입력으로 하여 IoT 네트워크에 대한 공격 여부를 탐지하는 공격 탐지 모델을 완성하여 저장하는 단계를 포함할 수 있다.
AbstractList The present invention relates to a method and apparatus for detecting an attack coming from the outside in a network formed of IoT equipment and, more specifically, to a method and apparatus for detecting an external attack by using traffic data collected from an IoT network. According to one embodiment of the present invention, the method comprises the following steps of: collecting traffic data packets for an IoT network; processing the traffic data packets to extract feature vectors; and executing an attack detection model to detect whether there is an attack on the IoT network corresponding to the feature vector. Before the collection step, the method includes a step of generating the attack detection model. The attack detection model generation step includes a step of using the feature vector, as a result of processing traffic data packets in a steady state collected from the IoT network, as an input to train an unsupervised learning-based deep neural network model and a step of using the feature vector as an input through training of the deep neural network to complete and store the attack detection model detecting an attack in the IoT network. 본 발명은 IoT 장비로 구성된 네트워크에서 외부로부터 들어오는 공격을 탐지하기 위한 방법 및 장치에 관한 것으로서, IoT 네트워크에서 수집된 트래픽 데이터를 활용하여 외부로부터의 공격을 탐지하는 방법 및 장치에 관한 것이다. 본 발명의 일 실시 예에 따른 네트워크 공격 탐지 방법은, IoT 네트워크에 대한 트래픽 데이터 패킷을 수집하는 단계와, 트래픽 데이터 패킷을 가공하여 특성 벡터를 추출하는 단계와, 공격 탐지 모델을 실행하여 특성 벡터에 대응하는 IoT 네트워크에 대한 공격 여부를 탐지하는 단계를 포함하고, 수집하는 단계 이전에, 공격 탐지 모델을 생성하는 단계를 더 포함하고, 공격 탐지 모델을 생성하는 단계는, IoT 네트워크로부터 수집한 정상 상태의 트래픽 데이터 패킷에 대한 가공 결과로서의 특성 벡터를 입력으로 하여 비지도 학습 기반의 심층신경망 모델을 훈련시키는 단계와, 심층신경망의 훈련을 통하여, 특성 벡터를 입력으로 하여 IoT 네트워크에 대한 공격 여부를 탐지하는 공격 탐지 모델을 완성하여 저장하는 단계를 포함할 수 있다.
Author CHUN SE LIN
KWON TAE KYOUNG
Author_xml – fullname: CHUN SE LIN
– fullname: KWON TAE KYOUNG
BookMark eNrjYmDJy89L5WQw8XUN8fB3UXD0A-KAAMcgx5DQYAU3_yAFF9cQV-cQTz93BceQEEdnbwVPPwU_15Bw_yBvHgbWtMSc4lReKM3NoOzmGuLsoZtakB-fWlyQmJyal1oS7x1kZGBkZGBgbmhhbuFoTJwqAFLUKds
ContentType Patent
DBID EVB
DatabaseName esp@cenet
DatabaseTitleList
Database_xml – sequence: 1
  dbid: EVB
  name: esp@cenet
  url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Chemistry
Sciences
Physics
DocumentTitleAlternate 네트워크 공격 탐지 방법 및 장치
ExternalDocumentID KR20220071878A
GroupedDBID EVB
ID FETCH-epo_espacenet_KR20220071878A3
IEDL.DBID EVB
IngestDate Fri Aug 30 05:41:51 EDT 2024
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
Korean
LinkModel DirectLink
MergedId FETCHMERGED-epo_espacenet_KR20220071878A3
Notes Application Number: KR20210100515
OpenAccessLink https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220531&DB=EPODOC&CC=KR&NR=20220071878A
ParticipantIDs epo_espacenet_KR20220071878A
PublicationCentury 2000
PublicationDate 20220531
PublicationDateYYYYMMDD 2022-05-31
PublicationDate_xml – month: 05
  year: 2022
  text: 20220531
  day: 31
PublicationDecade 2020
PublicationYear 2022
RelatedCompanies SEOUL NATIONAL UNIVERSITY R&DB FOUNDATION
RelatedCompanies_xml – name: SEOUL NATIONAL UNIVERSITY R&DB FOUNDATION
Score 3.380102
Snippet The present invention relates to a method and apparatus for detecting an attack coming from the outside in a network formed of IoT equipment and, more...
SourceID epo
SourceType Open Access Repository
SubjectTerms CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC COMMUNICATION TECHNIQUE
ELECTRICITY
INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS
PHYSICS
TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION
Title METHOD AND APPARATUS FOR DETECTING ATTACK IN NETWORK
URI https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220531&DB=EPODOC&locale=&CC=KR&NR=20220071878A
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfR3LTsJAcIL4vClKfKDZRMOtEdtC2wMxZbsINrRNXZQb6faRGE0hUuPvO1tAOXHYw-4kk9lN5v1YgDuBOsbKDE15iK1M0aPYVCJhqEpk6SJJM_SDYhmHHHmdwVh_nrQnFfhc98KUc0J_yuGIyFEx8ntRyuv5fxDLKWsrF_fiHY9mj33edZor71h2jaJQcXpdFviOT5uUdt2w6YVLGKpT0zDtHdiVhrSctM9ee7IvZb6pVPrHsBcgvrw4gcrHrAaHdP33Wg0ORquUdw32yxrNeIGHKz5cnII-YnzgO8T2cAWBHdp8_ELQoSMO44zyofdEbM5t6pKhRzzG3_zQPYPbPuN0oCAh0797T91wk2qtDtV8lqfnQKQbEbcTkWlovKntzGyJpBUJK9VFlHQM9QIa2zBdbgdfwZHcLlPkDagWX9_pNWreQtyUD_YLWmqBTw
link.rule.ids 230,309,786,891,25594,76903
linkProvider European Patent Office
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dT8JADG8QP_BNUeMH6iUa3hYRBtseiBm34XDstsxDeSO7fSRGA0Rm_PftTlCeeLiXNml6l7S9X3vtAdwKjDFGprWU-9jIFDWKdSUSWlOJDFUkaYY4KC7ykB7rOCP1adwel-Bj1Qsj54R-y-GIaFEx2nsu_fX8P4llybeVizvxhqTZQ593rfoSHRddo-hUrF7XDnzLp3VKu25YZ-EvD8OprunmFmxrCAolWHrpFX0p8_Wg0j-AnQDlTfNDKL3PqlChq7_XqrDnLUveVdiVbzTjBRKXdrg4AtWzueNbxGS4gsAMTT56JgjoiGVzm_IBeyQm5yZ1yYARZvNXP3SP4aZvc-ooqMjkb98TN1zXunUC5elsmp4CKWBE3E5E1sLLW7Od6Q2RNCJhpKqIko7WPIPaJknnm9nXUHG4N5wMB8y9gP2C9Vsur0E5__xKLzEK5-JKHt4Pi2CEOQ
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=METHOD+AND+APPARATUS+FOR+DETECTING+ATTACK+IN+NETWORK&rft.inventor=CHUN+SE+LIN&rft.inventor=KWON+TAE+KYOUNG&rft.date=2022-05-31&rft.externalDBID=A&rft.externalDocID=KR20220071878A