YorkSpace has migrated to a new version of its software. Access our Help Resources to learn how to use the refreshed site. Contact diginit@yorku.ca if you have any questions about the migration.
 

Novel Examination of Interpretable Surrogates and Adversarial Robustness in Machine Learning

Simple item page
dc.contributor.advisorUrner, Ruth
dc.contributor.authorChowdhury, Sadia
dc.date.accessioned2021-07-06T12:42:42Z
dc.date.available2021-07-06T12:42:42Z
dc.date.copyright2021-02
dc.date.issued2021-07-06
dc.date.updated2021-07-06T12:42:42Z
dc.degree.disciplineComputer Science
dc.degree.levelMaster's
dc.degree.nameMSc - Master of Science
dc.description.abstractThe lack of transparent output behavior is a significant source of mistrust in many of the currently most successful machine learning tools. Concern arises particularly in situations where the data generation changes, for example under marginal shift or under adversarial manipulations. We analyze the use of decision trees (a human interpretable model) for indicating marginal shift. We then investigate the role of the data generation for the validity of the interpretable surrogate and its implementation as both local and global interpretation methods. We often observed that the decision boundaries of the blackbox model was mostly sitting close to the original data manifold. This makes those regions vulnerable to imperceptible perturbations. Hence, we carefully argue that adversarial robustness should be defined as a locally adaptive measure complying with the underlying distribution. We then suggest a definition for an adaptive robust loss, an empirical version of it and a resulting data-augmentation framework.
dc.identifier.urihttp://hdl.handle.net/10315/38437
dc.languageen
dc.rightsAuthor owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.
dc.subjectComputer science
dc.subject.keywordsMachine Learning
dc.subject.keywordsInterpretability
dc.subject.keywordsAdversarial Examples
dc.subject.keywordsRobustness
dc.subject.keywordsDecision Trees
dc.subject.keywordsNeural Networks
dc.subject.keywordsBinary Loss
dc.subject.keywordsRobust Loss
dc.titleNovel Examination of Interpretable Surrogates and Adversarial Robustness in Machine Learning
dc.typeElectronic Thesis or Dissertation

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Chowdhury_Sadia_2021_MSc.pdf
Size:
7.2 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
license.txt
Size:
1.87 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
YorkU_ETDlicense.txt
Size:
3.39 KB
Format:
Plain Text
Description:
Download

Collections

Computer Science

All items in the YorkSpace institutional repository are protected by copyright, with all rights reserved except where explicitly noted.