Data Correction For Enhancing Classification Accuracy By Unknown Deep Neural Network Classifiers

Cited 3 time in webofscience Cited 0 time in scopus
  • Hit : 101
  • Download : 9
DC FieldValueLanguage
dc.contributor.authorKwon, Hyunko
dc.contributor.authorYoon, Hyunsooko
dc.contributor.authorChoi, Daeseonko
dc.date.accessioned2021-10-31T06:43:00Z-
dc.date.available2021-10-31T06:43:00Z-
dc.date.created2021-10-31-
dc.date.created2021-10-31-
dc.date.created2021-10-31-
dc.date.created2021-10-31-
dc.date.issued2021-09-
dc.identifier.citationKSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS, v.15, no.9, pp.3243 - 3257-
dc.identifier.issn1976-7277-
dc.identifier.urihttp://hdl.handle.net/10203/288476-
dc.description.abstractDeep neural networks provide excellent performance in pattern recognition, audio classification, and image recognition. It is important that they accurately recognize input data, particularly when they are used in autonomous vehicles or for medical services. In this study, we propose a data correction method for increasing the accuracy of an unknown classifier by modifying the input data without changing the classifier. This method modifies the input data slightly so that the unknown classifier will correctly recognize the input data. It is an ensemble method that has the characteristic of transferability to an unknown classifier by generating corrected data that are correctly recognized by several classifiers that are known in advance. We tested our method using MNIST and CIFAR-10 as experimental data. The experimental results exhibit that the accuracy of the unknown classifier is a 100% correct recognition rate owing to the data correction generated by the proposed method, which minimizes data distortion to maintain the data's recognizability by humans.-
dc.languageEnglish-
dc.publisherKSII-KOR SOC INTERNET INFORMATION-
dc.titleData Correction For Enhancing Classification Accuracy By Unknown Deep Neural Network Classifiers-
dc.typeArticle-
dc.identifier.wosid000704414500009-
dc.identifier.scopusid2-s2.0-85117105934-
dc.type.rimsART-
dc.citation.volume15-
dc.citation.issue9-
dc.citation.beginningpage3243-
dc.citation.endingpage3257-
dc.citation.publicationnameKSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS-
dc.identifier.doi10.3837/tiis.2021.09.009-
dc.embargo.liftdate9999-12-31-
dc.embargo.terms9999-12-31-
dc.identifier.kciidART002761101-
dc.contributor.localauthorYoon, Hyunsoo-
dc.contributor.nonIdAuthorKwon, Hyun-
dc.contributor.nonIdAuthorChoi, Daeseon-
dc.description.isOpenAccessN-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorData correction-
dc.subject.keywordAuthorDeep neural network-
dc.subject.keywordAuthorEnsemble method-
dc.subject.keywordAuthorMachine learning-
dc.subject.keywordAuthorPoisoning attack-
Appears in Collection
CS-Journal Papers(저널논문)
Files in This Item
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 3 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0