Role of Spatial Context in Adversarial Robustness for Object Detection

Simple item page
dc.contributor.authorSaha, Aniruddha
dc.contributor.authorSubramanya, Akshayvarun
dc.contributor.authorPatil, Koninika
dc.contributor.authorPirsiavash, Hamed
dc.date.accessioned2020-09-22T17:00:27Z
dc.date.available2020-09-22T17:00:27Z
dc.description.abstractThe benefits of utilizing spatial context in fast object detection algorithms have been studied extensively. Detectors increase inference speed by doing a single forward pass per image which means they implicitly use contextual reasoning for their predictions. However, one can show that an adversary can design adversarial patches which do not overlap with any objects of interest in the scene and exploit contextual reasoning to fool standard detectors. In this paper, we examine this problem and design category specific adversarial patches which make a widely used object detector like YOLO blind to an attacker chosen object category. We also show that limiting the use of spatial context during object detector training improves robustness to such adversaries. We believe the existence of context based adversarial attacks is concerning since the adversarial patch can affect predictions without being in vicinity of any objects of interest. Hence, defending against such attacks becomes challenging and we 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://ieeexplore.ieee.org/document/9150650en_US
dc.format.extent10 pagesen_US
dc.genreconference papers and proceedings postprintsen_US
dc.identifierdoi:10.1109/CVPRW50498.2020.00400
dc.identifier.citationA. Saha, A. Subramanya, K. Patil and H. Pirsiavash, "Role of Spatial Context in Adversarial Robustness for Object Detection," 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA, 2020, pp. 3403-3412, doi: 10.1109/CVPRW50498.2020.00400.en_US
dc.identifier.urihttp://hdl.handle.net/11603/19708
dc.language.isoen_USen_US
dc.publisherIEEEen_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.rights© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
dc.titleRole of Spatial Context in Adversarial Robustness for Object Detectionen_US
dc.typeTexten_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Saha_Role_of_Spatial_Context_in_Adversarial_Robustness_for_Object_Detection_CVPRW_2020_paper.pdf
Size:
1.43 MB
Format:
Adobe Portable Document Format
Description:
Download
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