International Journal of Computational Intelligence Systems

Volume 14, Issue 1, 2021, Pages 1823 - 1830

Fast Category-Hidden Adversarial Attack Against Semantic Image Segmentation

Authors
Yinghui Zhu, Yuzhen Jiang*, ORCID, Zhongxing Peng, Wei Huang
School of Computer and Information Engineering, Hanshan Normal University, Qiaodong Street, Xiangqiao District Chaozhou, 521041, P. R. China
*Corresponding author. E-mail: jyz366@163.com
Corresponding Author
Yuzhen Jiang
Received 23 February 2021, Accepted 9 June 2021, Available Online 28 June 2021.
DOI
10.2991/ijcis.d.210620.002How to use a DOI?
Keywords
Adversarial example; Deep neural networks (DNNs); Semantic segmentation; Category-hidden adversarial attack (CHAA); Logits map
Abstract

In semantic segmentation, category-hidden attack is a malicious adversarial attack which manipulates a specific category without affecting the recognition of other objects. A popular method is the nearest-neighbor algorithm, which modifies the segmentation map by replacing a target category with other categories close to it. Nearest-neighbor method aims to restrict the strength of perturbation noise that is imperceptive to both human eyes and segmentation algorithms. However, its spatial search adds lots of computational burden. In this paper, we propose two fast methods, dot-based method and line-based method, which are able to quickly complete the category transfers in logits maps without spatial search. The advantages of our two methods result from generating the logits maps by modifying the probability distribution of the category channels. Both of our methods are global, and the location and size of objects to hide are not cared, so their processing speed is very fast. The dot-based algorithm takes the pixel as the unit of calculation, and the line-based algorithm combines the category distribution characteristics of the horizontal direction to calculate. Experiments verify the effectiveness and efficiency compared with nearest-neighbor method. Specifically, in the segmentation map modification step, our methods are 5 times and 65 times faster than nearest-neighbor, respectively. In the small perturbation attack experiment, dot-based method gets the fastest speed, while different datasets and different setting experiments indicate that the line-based method is able to achieve faster and better adversarial segmentation results in most cases.

Copyright
© 2021 The Authors. Published by Atlantis Press B.V.
Open Access
This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)
View full text (HTML)

Journal
International Journal of Computational Intelligence Systems
Volume-Issue
14 - 1
Pages
1823 - 1830
Publication Date
2021/06/28
ISSN (Online)
1875-6883
ISSN (Print)
1875-6891
DOI
10.2991/ijcis.d.210620.002How to use a DOI?
Copyright
© 2021 The Authors. Published by Atlantis Press B.V.
Open Access
This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - JOUR
AU  - Yinghui Zhu
AU  - Yuzhen Jiang
AU  - Zhongxing Peng
AU  - Wei Huang
PY  - 2021
DA  - 2021/06/28
TI  - Fast Category-Hidden Adversarial Attack Against Semantic Image Segmentation
JO  - International Journal of Computational Intelligence Systems
SP  - 1823
EP  - 1830
VL  - 14
IS  - 1
SN  - 1875-6883
UR  - https://doi.org/10.2991/ijcis.d.210620.002
DO  - 10.2991/ijcis.d.210620.002
ID  - Zhu2021
ER  -