Show simple item record

dc.contributor.advisorLuca Daniel.en_US
dc.contributor.authorWeng, Tsui-Wei(Tsui-Wei Lily)en_US
dc.contributor.otherMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.en_US
dc.date.accessioned2021-01-06T20:18:04Z
dc.date.available2021-01-06T20:18:04Z
dc.date.copyright2020en_US
dc.date.issued2020en_US
dc.identifier.urihttps://hdl.handle.net/1721.1/129313
dc.descriptionThesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, September, 2020en_US
dc.descriptionCataloged from student-submitted PDF of thesis.en_US
dc.descriptionIncludes bibliographical references (pages 135-143).en_US
dc.description.abstractThe robustness of neural networks to adversarial examples has received great attention due to security implications. Despite various attack approaches to crafting visually imperceptible adversarial examples, little has been developed towards a comprehensive metric of robustness. This thesis is dedicated to developing several robustness quantification frameworks for deep neural networks against both adversarial and non-adversarial input perturbations, including the first robustness score CLEVER, efficient certification algorithms Fast-Lin, CROWN, CNN-Cert, and probabilistic robustness verification algorithm PROVEN. Our proposed approaches are computationally efficient and provide good quality of robustness estimates and certificates as demonstrated by extensive experiments on MNIST, CIFAR and ImageNet.en_US
dc.description.statementofresponsibilityby Tsui-Wei (Lily) Weng.en_US
dc.format.extent143 pagesen_US
dc.language.isoengen_US
dc.publisherMassachusetts Institute of Technologyen_US
dc.rightsMIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided.en_US
dc.rights.urihttp://dspace.mit.edu/handle/1721.1/7582en_US
dc.subjectElectrical Engineering and Computer Science.en_US
dc.titleEvaluating robustness of neural networksen_US
dc.typeThesisen_US
dc.description.degreePh. D.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.identifier.oclc1227782217en_US
dc.description.collectionPh.D. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Scienceen_US
dspace.imported2021-01-06T20:18:02Zen_US
mit.thesis.degreeDoctoralen_US
mit.thesis.departmentEECSen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record