Repository logo
 

Utilizing network features to detect erroneous inputs

Simple item page
dc.contributor.authorGorbett, Matthew, author
dc.contributor.authorBlanchard, Nathaniel, advisor
dc.contributor.authorAnderson, Charles W., committee member
dc.contributor.authorKing, Emily, committee member
dc.date.accessioned2021-01-11T11:20:26Z
dc.date.available2021-01-11T11:20:26Z
dc.date.issued2020
dc.description.abstractNeural networks are vulnerable to a wide range of erroneous inputs such as corrupted, out-of-distribution, misclassified, and adversarial examples. Previously, separate solutions have been proposed for each of these faulty data types; however, in this work I show that the collective set of erroneous inputs can be jointly identified with a single model. Specifically, I train a linear SVM classifier to detect these four types of erroneous data using the hidden and softmax feature vectors of pre-trained neural networks. Results indicate that these faulty data types generally exhibit linearly separable activation properties from correctly processed examples. I am able to identify erroneous inputs with an AUROC of 0.973 on CIFAR10, 0.957 on Tiny ImageNet, and 0.941 on ImageNet. I experimentally validate the findings across a diverse range of datasets, domains, and pre-trained models.
dc.format.mediumborn digital
dc.format.mediummasters theses
dc.identifierGorbett_colostate_0053N_16397.pdf
dc.identifier.urihttps://hdl.handle.net/10217/219573
dc.languageEnglish
dc.language.isoeng
dc.publisherColorado State University. Libraries
dc.relation.ispartof2020-
dc.rightsCopyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright.
dc.titleUtilizing network features to detect erroneous inputs
dc.typeText
dcterms.rights.dplaThis Item is protected by copyright and/or related rights (https://rightsstatements.org/vocab/InC/1.0/). You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).
thesis.degree.disciplineComputer Science
thesis.degree.grantorColorado State University
thesis.degree.levelMasters
thesis.degree.nameMaster of Science (M.S.)

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Gorbett_colostate_0053N_16397.pdf
Size:
1.83 MB
Format:
Adobe Portable Document Format
Download

Collections

2020-
Theses and Dissertations