Diao, Y, Shao, T, Yang, Y-L et al. (2 more authors) (2021) BASAR:Black-box Attack on Skeletal Action Recognition. In: Proccedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). The Conference on Computer Vision and Pattern Recognition, 14-19 Jun 2021, Online. IEEE , pp. 7593-7603. ISBN 978-1-6654-4509-2
Abstract
Skeletal motion plays a vital role in human activity recognition as either an independent data source or a complement [33]. The robustness of skeleton-based activity recognizers has been questioned recently [29], [50], which shows that they are vulnerable to adversarial attacks when the full-knowledge of the recognizer is accessible to the attacker. However, this white-box requirement is overly restrictive in most scenarios and the attack is not truly threatening. In this paper, we show that such threats do exist under black-box settings too. To this end, we propose the first black-box adversarial attack method BASAR. Through BASAR, we show that adversarial attack is not only truly a threat but also can be extremely deceitful, because on-manifold adversarial samples are rather common in skeletal motions, in contrast to the common belief that adversarial samples only exist off-manifold [18]. Through exhaustive evaluation and comparison, we show that BASAR can deliver successful attacks across models, data, and attack modes. Through harsh perceptual studies, we show that it achieves effective yet imperceptible attacks. By analyzing the attack on different activity recognizers, BASAR helps identify the potential causes of their vulnerability and provides insights on what classifiers are likely to be more robust against attack.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2021 by The Institute of Electrical and Electronics Engineers, Inc. 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. |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) |
Funding Information: | Funder Grant number EPSRC (Engineering and Physical Sciences Research Council) EP/R031193/1 EU - European Union 899739 |
Depositing User: | Symplectic Publications |
Date Deposited: | 11 Mar 2021 17:35 |
Last Modified: | 18 Jan 2024 16:46 |
Status: | Published |
Publisher: | IEEE |
Identification Number: | 10.1109/CVPR46437.2021.00751 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:171782 |