Adversarial Attacks for Network Interpretation

Simple item page
dc.contributor.advisorPirsiavash, Hamed
dc.contributor.authorPillai, Vipin Radhakrishnan
dc.contributor.departmentComputer Science and Electrical Engineering
dc.contributor.programComputer Science
dc.date.accessioned2021-01-29T18:12:32Z
dc.date.available2021-01-29T18:12:32Z
dc.date.issued2018-01-01
dc.description.abstractAdversarial attacks are known to fool deep neural networks to produce incorrect predictions. We introduce adversarial attack algorithms that not only fool the network's prediction, but also fool our interpretation of the cause of the network's decision. We show that our algorithms can empower practical adversarial attacks, like adversarial patches, by hiding them from network interpretation tools. We also introduce adversarial attack algorithms which can change the interpretation of the network's decision without changing the network's output. We show that our attack tuned for GradCam visualization transfers directly to other visualization algorithms like CAM and occluding patch as well. We believe our algorithms can facilitate developing more robust network interpretation tools that truly explain the network's underlying decision-making process.
dc.formatapplication:pdf
dc.genretheses
dc.identifierdoi:10.13016/m2mtb1-e3w7
dc.identifier.other11892
dc.identifier.urihttp://hdl.handle.net/11603/20719
dc.languageen
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department Collection
dc.relation.ispartofUMBC Theses and Dissertations Collection
dc.relation.ispartofUMBC Graduate School Collection
dc.relation.ispartofUMBC Student Collection
dc.sourceOriginal File Name: Pillai_umbc_0434M_11892.pdf
dc.subjectAdversarial Attacks
dc.subjectConvolutional Neural Networks
dc.subjectExplainable AI
dc.subjectImage Classification
dc.subjectNetwork Interpretation
dc.titleAdversarial Attacks for Network Interpretation
dc.typeText
dcterms.accessRightsDistribution Rights granted to UMBC by the author.
dcterms.accessRightsAccess limited to the UMBC community. Item may possibly be obtained via Interlibrary Loan thorugh a local library, pending author/copyright holder's permission.
dcterms.accessRightsThis 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.

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Pillai_umbc_0434M_11892.pdf
Size:
3.93 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
PillaiVAdversarial_Open.pdf
Size:
43.51 KB
Format:
Adobe Portable Document Format
Description:
Download

Collections

UMBC Theses and Dissertations
UMBC Computer Science and Electrical Engineering Department
UMBC Graduate School
UMBC Student Collection