Conference item icon

Conference item

RANCER: non-axis aligned anisotropic certification with randomized smoothing

Abstract:
As modern networks have been proven to be unprotected from adversarial attacks and are applied in safety-critical applications, defense against them is very crucial. Many works were dedicated to this topic, but randomized smoothing has been recently proven to be an effective approach for the certified defense of deep neural networks and getting robust classifiers. Some prior results were obtained utilizing the techniques of adding extra parameters to extend the limits of the certification regions. In this way, sample-wise optimization was proposed to maximize the certification radius per input. The idea was further extended with the generalized anisotropic counterparts of ℓ 1 and ℓ 2 certificates which allow achieving larger certified region volume avoiding worst-case certification near potentially larger safe regions. However, anisotropic certification is limited by the aligned axis lacking the freedom to extend in any direction. To mitigate this constraint, in this work, we (i) revisit the anisotropic certification, provide an analysis of its non-axis aligned counterpart and propose its rotation-free extension, (ii) conduct experiments on the CIFAR-10 dataset to report the improved performance.
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1109/wacv56688.2023.00465

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author


Publisher:
IEEE
Host title:
2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Pages:
2472-6737
Place of publication:
Los Alamitos, California
Publication date:
2023-02-06
Acceptance date:
2022-08-15
Event title:
2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Event series:
Winter Conference on Applications of Computer Vision
Event location:
Waikoloa, HI, USA
Event website:
https://wacv2023.thecvf.com/home
Event start date:
2023-01-03
Event end date:
2023-01-07
DOI:
EISSN:
2642-9381
ISSN:
2472-6737
ISBN:
978-1-6654-9346-8


Language:
English
Keywords:
Pubs id:
1328296
Local pid:
pubs:1328296
Deposit date:
2023-02-10

Terms of use



Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP