Utilizing network features to detect erroneous inputs
dc.contributor.author | Gorbett, Matthew, author | |
dc.contributor.author | Blanchard, Nathaniel, advisor | |
dc.contributor.author | Anderson, Charles W., committee member | |
dc.contributor.author | King, Emily, committee member | |
dc.date.accessioned | 2021-01-11T11:20:26Z | |
dc.date.available | 2021-01-11T11:20:26Z | |
dc.date.issued | 2020 | |
dc.description.abstract | Neural 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.medium | born digital | |
dc.format.medium | masters theses | |
dc.identifier | Gorbett_colostate_0053N_16397.pdf | |
dc.identifier.uri | https://hdl.handle.net/10217/219573 | |
dc.language | English | |
dc.language.iso | eng | |
dc.publisher | Colorado State University. Libraries | |
dc.relation.ispartof | 2020- | |
dc.rights | Copyright 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.title | Utilizing network features to detect erroneous inputs | |
dc.type | Text | |
dcterms.rights.dpla | This 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.discipline | Computer Science | |
thesis.degree.grantor | Colorado State University | |
thesis.degree.level | Masters | |
thesis.degree.name | Master of Science (M.S.) |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Gorbett_colostate_0053N_16397.pdf
- Size:
- 1.83 MB
- Format:
- Adobe Portable Document Format