Physical Adversarial Attacks on an Aerial Imagery Object Detector

Date

2022

Authors

Du, A.
Chen, B.
Chin, T.J.
Law, Y.W.
Sasdelli, M.
Raja Segaran, R.
Campbell, D.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

Proceedings 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2022), 2022, pp.3798-3808

Statement of Responsibility

Andrew Du, Bo Chen, Tat-Jun Chin, Yee Wei Law, Michele Sasdelli, Ramesh Rajasegaran, Dillon Campbell

Conference Name

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (4 Jan 2022 - 8 Jan 2022 : Waikoloa, Hawaii)

Abstract

Deep 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.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

©2021 IEEE

License

Grant ID

Call number

Persistent link to this record