Physical Adversarial Attacks on an Aerial Imagery Object Detector

Simple item page
dc.contributor.authorDu, A.
dc.contributor.authorChen, B.
dc.contributor.authorChin, T.J.
dc.contributor.authorLaw, Y.W.
dc.contributor.authorSasdelli, M.
dc.contributor.authorRaja Segaran, R.
dc.contributor.authorCampbell, D.
dc.contributor.conferenceIEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (4 Jan 2022 - 8 Jan 2022 : Waikoloa, Hawaii)
dc.date.issued2022
dc.description.abstractDeep neural networks (DNNs) have become essential for processing the vast amounts of aerial imagery collected using earth-observing satellite platforms. However, DNNs are vulnerable towards adversarial examples, and it is expected that this weakness also plagues DNNs for aerial imagery. In this work, we demonstrate one of the first efforts on physical adversarial attacks on aerial imagery, whereby adversarial patches were optimised, fabricated and installed on or near target objects (cars) to significantly reduce the efficacy of an object detector applied on overhead images. Physical adversarial attacks on aerial images, particularly those captured from satellite platforms, are challenged by atmospheric factors (lighting, weather, seasons) and the distance between the observer and target. To investigate the effects of these challenges, we devised novel experiments and metrics to evaluate the efficacy of physical adversarial attacks against object detectors in aerial scenes. Our results indicate the palpable threat posed by physical adversarial attacks towards DNNs for processing satellite imagery.
dc.description.statementofresponsibilityAndrew Du, Bo Chen, Tat-Jun Chin, Yee Wei Law, Michele Sasdelli, Ramesh Rajasegaran, Dillon Campbell
dc.identifier.citationProceedings 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2022), 2022, pp.3798-3808
dc.identifier.doi10.1109/WACV51458.2022.00385
dc.identifier.isbn9781665409162
dc.identifier.issn2472-6737
dc.identifier.issn2642-9381
dc.identifier.orcidDu, A. [0000-0003-0157-6426]
dc.identifier.orcidChen, B. [0000-0002-1589-8082]
dc.identifier.orcidSasdelli, M. [0000-0003-1021-6369]
dc.identifier.orcidRaja Segaran, R. [0000-0002-0484-8194]
dc.identifier.urihttps://hdl.handle.net/2440/135526
dc.language.isoen
dc.publisherIEEE
dc.publisher.placeOnline
dc.relation.ispartofseriesIEEE Winter Conference on Applications of Computer Vision
dc.rights©2021 IEEE
dc.source.urihttps://ieeexplore.ieee.org/xpl/conhome/9706406/proceeding
dc.titlePhysical Adversarial Attacks on an Aerial Imagery Object Detector
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Computer Science publications