Fooling Network Interpretation in Image Classification

Simple item page
dc.contributor.authorSubramanya, Akshayvarun
dc.contributor.authorPillai, Vipin
dc.contributor.authorPirsiavash, Hamed
dc.date.accessioned2020-03-11T18:12:18Z
dc.date.available2020-03-11T18:12:18Z
dc.date.issued2019-09-24
dc.description.abstractDeep neural networks have been shown to be fooled rather easily using adversarial attack algorithms. Practical methods such as adversarial patches have been shown to be extremely effective in causing misclassification. However, these patches are highlighted using standard network interpretation algorithms, thus revealing the identity of the adversary. We show that it is possible to create adversarial patches which not only fool the prediction, but also change what we interpret regarding the cause of the prediction. Moreover, we introduce our attack as a controlled setting to measure the accuracy of interpretation algorithms. We show this using extensive experiments for Grad-CAM interpretation that transfers to occluding patch interpretation as well. We believe our algorithms can facilitate developing more robust network interpretation tools that truly explain the network's underlying decision making process.en_US
dc.description.sponsorshipThis work was performed under the following financial assistance award: 60NANB18D279 from U.S. Department of Commerce, National Institute of Standards and Technology, funding from SAP SE, and also NSF grant 1845216.en_US
dc.description.urihttps://arxiv.org/abs/1812.02843en_US
dc.format.extent18 pagesen_US
dc.genrejournal articles preprintsen_US
dc.identifierdoi:10.13016/m22dqb-1n5i
dc.identifier.citationSubramanya, Akshayvarun; Pillai, Vipin; Pirsiavash, Hamed; Fooling Network Interpretation in Image Classification; Computer Vision and Pattern Recognition (2019); https://arxiv.org/abs/1812.02843en_US
dc.identifier.urihttp://hdl.handle.net/11603/17552
dc.language.isoen_USen_US
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department Collection
dc.relation.ispartofUMBC Student Collection
dc.relation.ispartofUMBC Faculty Collection
dc.rightsThis item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
dc.subjectdeep neural networksen_US
dc.subjectalgorithmsen_US
dc.subjectadversarial patchesen_US
dc.subjectmisclassificationen_US
dc.titleFooling Network Interpretation in Image Classificationen_US
dc.typeTexten_US

Files

License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.56 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection
UMBC Student Collection