Adversarial Patches Exploiting Contextual Reasoning in Object Detection

Simple item page
dc.contributor.authorSaha, Aniruddha
dc.contributor.authorSubramanya, Akshayvarun
dc.contributor.authorPatil, Koninika
dc.date.accessioned2020-03-11T17:22:19Z
dc.date.available2020-03-11T17:22:19Z
dc.date.issued2019-12-21
dc.description.abstractThe utilization of spatial context to improve accuracy in most fast object detection algorithms is well known. The detectors increase inference speed by doing a single forward pass per image which means they implicitly use contextual reasoning for their predictions. We show that an adversary can exploit such contextual reasoning to fool standard detectors. We develop adversarial patches that make an object detector blind to a particular category even though the patch does not overlap with the missed detections. We also study methods to fix this vulnerability and show that limiting the use of contextual reasoning during object detector training acts as a form of defense that makes the detector robust. We believe defending against context based adversarial attack algorithms is not easy. We take a step towards that direction and urge the research community to give attention to this vulnerability.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/1910.00068en_US
dc.format.extent15 pagesen_US
dc.genrejournal articles preprintsen_US
dc.identifierdoi:10.13016/m2nx1l-q6od
dc.identifier.citationSaha, Aniruddha; Subramanya, Akshayvarun; Patil, Koninika; Adversarial Patches Exploiting Contextual Reasoning in Object Detection; Computer Vision and Pattern Recognition (2019); https://arxiv.org/abs/1910.00068en_US
dc.identifier.urihttp://hdl.handle.net/11603/17548
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.subjectspatial contexten_US
dc.subjectcontextual reasoningen_US
dc.subjectadversarial patchesen_US
dc.subjectobject detectoren_US
dc.titleAdversarial Patches Exploiting Contextual Reasoning in Object Detectionen_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