On the Interplay of Convolutional Padding and Adversarial Robustness
- It is common practice to apply padding prior to convolution operations to preserve the resolution of feature-maps in Convolutional Neural Networks (CNN). While many alternatives exist, this is often achieved by adding a border of zeros around the inputs. In this work, we show that adversarial attacks often result in perturbation anomalies at the image boundaries, which are the areas where paddingIt is common practice to apply padding prior to convolution operations to preserve the resolution of feature-maps in Convolutional Neural Networks (CNN). While many alternatives exist, this is often achieved by adding a border of zeros around the inputs. In this work, we show that adversarial attacks often result in perturbation anomalies at the image boundaries, which are the areas where padding is used. Consequently, we aim to provide an analysis of the interplay between padding and adversarial attacks and seek an answer to the question of how different padding modes (or their absence) affect adversarial robustness in various scenarios.…
Document Type: | Conference Proceeding |
---|---|
Conference Type: | Konferenzartikel |
Zitierlink: | https://opus.hs-offenburg.de/8244 | Bibliografische Angaben |
Title (English): | On the Interplay of Convolutional Padding and Adversarial Robustness |
Conference: | IEEE/CVF International Conference on Computer Vision Workshops (02-06 October 2023 : Paris, France) |
Author: | Paul GavrikovStaff MemberORCiDGND, Janis KeuperStaff MemberORCiDGND |
Year of Publication: | 2023 |
Creating Corporation: | Computer Vision Foundation |
First Page: | 3981 |
Last Page: | 3990 |
Parent Title (English): | Proceedings : 2023 IEEE/CVF International Conference on Computer Vision Workshops : ICCVW 2023 |
ISBN: | 979-8-3503-0744-3 (Elektronisch) |
ISBN: | 979-8-3503-0745-0 (Print on Demand) |
DOI: | https://doi.org/10.1109/ICCVW60793.2023.00430 |
URL: | https://openaccess.thecvf.com/content/ICCV2023W/BRAVO/papers/Gavrikov_On_the_Interplay_of_Convolutional_Padding_and_Adversarial_Robustness_ICCVW_2023_paper.pdf |
Language: | English | Inhaltliche Informationen |
Institutes: | Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) |
Forschung / IMLA - Institute for Machine Learning and Analytics | |
Institutes: | Bibliografie |
Tag: | Deep Leaning | Formale Angaben |
Relevance: | Konferenzbeitrag: h5-Index > 30 |
Open Access: | Open Access |
Grün | |
Licence (German): | Urheberrechtlich geschützt |