Matches in SemOpenAlex for { <https://semopenalex.org/work/W1569223999> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W1569223999 abstract "Previous chapter Next chapter Full AccessProceedings Proceedings of the 2007 SIAM International Conference on Data Mining (SDM)Towards Attack-Resilient Geometric Data PerturbationKeke Chen, Gordon Sun, and Ling LiuKeke Chen, Gordon Sun, and Ling Liupp.78 - 89Chapter DOI:https://doi.org/10.1137/1.9781611972771.8PDFBibTexSections ToolsAdd to favoritesExport CitationTrack CitationsEmail SectionsAboutAbstract Data perturbation is a popular technique for privacy-preserving data mining. The major challenge of data perturbation is balancing privacy protection and data quality, which are normally considered as a pair of contradictive factors. We propose that selectively preserving only the task/model specific information in perturbation would improve the balance. Geometric data perturbation, consisting of random rotation perturbation, random translation perturbation, and noise addition, aims at preserving the important geometric properties of a multidimensional dataset, while providing better privacy guarantee for data classification modeling. The preliminary study has shown that random geometric perturbation can well preserve model accuracy for several popular classification models, including kernel methods, linear classifiers, and SVM classifiers, while it also revealed some security concerns to random geometric perturbation. In this paper, we address some potential attacks to random geometric perturbation and design several methods to reduce the threat of these attacks. Experimental study shows that the enhanced geometric perturbation can provide satisfactory privacy guarantee while still well preserving model accuracy for the discussed data classification models. Previous chapter Next chapter RelatedDetails Published:2007ISBN:978-0-89871-630-6eISBN:978-1-61197-277-1 https://doi.org/10.1137/1.9781611972771Book Series Name:ProceedingsBook Code:PR127Book Pages:xiv + 648" @default.
- W1569223999 created "2016-06-24" @default.
- W1569223999 creator A5002572745 @default.
- W1569223999 creator A5017360203 @default.
- W1569223999 date "2007-04-26" @default.
- W1569223999 modified "2023-10-18" @default.
- W1569223999 title "Towards Attack-Resilient Geometric Data Perturbation" @default.
- W1569223999 cites W129088861 @default.
- W1569223999 cites W1480376833 @default.
- W1569223999 cites W1544579602 @default.
- W1569223999 cites W1548802052 @default.
- W1569223999 cites W1999602050 @default.
- W1569223999 cites W2009733253 @default.
- W1569223999 cites W2022079499 @default.
- W1569223999 cites W2047370889 @default.
- W1569223999 cites W2055229738 @default.
- W1569223999 cites W2058977000 @default.
- W1569223999 cites W2078937669 @default.
- W1569223999 cites W2089817321 @default.
- W1569223999 cites W2093367651 @default.
- W1569223999 cites W2112022568 @default.
- W1569223999 cites W2122759946 @default.
- W1569223999 cites W2128906841 @default.
- W1569223999 cites W2130099852 @default.
- W1569223999 cites W2139336600 @default.
- W1569223999 cites W2141224535 @default.
- W1569223999 cites W2159024459 @default.
- W1569223999 cites W2161030490 @default.
- W1569223999 cites W2164341199 @default.
- W1569223999 doi "https://doi.org/10.1137/1.9781611972771.8" @default.
- W1569223999 hasPublicationYear "2007" @default.
- W1569223999 type Work @default.
- W1569223999 sameAs 1569223999 @default.
- W1569223999 citedByCount "88" @default.
- W1569223999 countsByYear W15692239992012 @default.
- W1569223999 countsByYear W15692239992013 @default.
- W1569223999 countsByYear W15692239992014 @default.
- W1569223999 countsByYear W15692239992015 @default.
- W1569223999 countsByYear W15692239992016 @default.
- W1569223999 countsByYear W15692239992017 @default.
- W1569223999 countsByYear W15692239992018 @default.
- W1569223999 countsByYear W15692239992019 @default.
- W1569223999 countsByYear W15692239992020 @default.
- W1569223999 countsByYear W15692239992021 @default.
- W1569223999 countsByYear W15692239992022 @default.
- W1569223999 countsByYear W15692239992023 @default.
- W1569223999 crossrefType "proceedings-article" @default.
- W1569223999 hasAuthorship W1569223999A5002572745 @default.
- W1569223999 hasAuthorship W1569223999A5017360203 @default.
- W1569223999 hasBestOaLocation W15692239992 @default.
- W1569223999 hasConcept C11413529 @default.
- W1569223999 hasConcept C119857082 @default.
- W1569223999 hasConcept C121332964 @default.
- W1569223999 hasConcept C124101348 @default.
- W1569223999 hasConcept C154945302 @default.
- W1569223999 hasConcept C169258074 @default.
- W1569223999 hasConcept C177918212 @default.
- W1569223999 hasConcept C41008148 @default.
- W1569223999 hasConcept C62520636 @default.
- W1569223999 hasConcept C80444323 @default.
- W1569223999 hasConceptScore W1569223999C11413529 @default.
- W1569223999 hasConceptScore W1569223999C119857082 @default.
- W1569223999 hasConceptScore W1569223999C121332964 @default.
- W1569223999 hasConceptScore W1569223999C124101348 @default.
- W1569223999 hasConceptScore W1569223999C154945302 @default.
- W1569223999 hasConceptScore W1569223999C169258074 @default.
- W1569223999 hasConceptScore W1569223999C177918212 @default.
- W1569223999 hasConceptScore W1569223999C41008148 @default.
- W1569223999 hasConceptScore W1569223999C62520636 @default.
- W1569223999 hasConceptScore W1569223999C80444323 @default.
- W1569223999 hasLocation W15692239991 @default.
- W1569223999 hasLocation W15692239992 @default.
- W1569223999 hasLocation W15692239993 @default.
- W1569223999 hasOpenAccess W1569223999 @default.
- W1569223999 hasPrimaryLocation W15692239991 @default.
- W1569223999 hasRelatedWork W2911455822 @default.
- W1569223999 hasRelatedWork W3174196512 @default.
- W1569223999 hasRelatedWork W3211546796 @default.
- W1569223999 hasRelatedWork W4281560664 @default.
- W1569223999 hasRelatedWork W4281616679 @default.
- W1569223999 hasRelatedWork W4293525103 @default.
- W1569223999 hasRelatedWork W4308191010 @default.
- W1569223999 hasRelatedWork W4318350883 @default.
- W1569223999 hasRelatedWork W4323021782 @default.
- W1569223999 hasRelatedWork W4364301731 @default.
- W1569223999 isParatext "false" @default.
- W1569223999 isRetracted "false" @default.
- W1569223999 magId "1569223999" @default.
- W1569223999 workType "article" @default.