中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Towards Robust Semantic Segmentation against Patch-Based Attack via Attention Refinement

文献类型：期刊论文

作者Yuan, Zheng1,2,3; Zhang, Jie1,2,3; Wang, Yude1,2,3; Shan, Shiguang1,2,3; Chen, Xilin1,2,3
刊名INTERNATIONAL JOURNAL OF COMPUTER VISION
出版日期2024-06-07
页码23
关键词Model robustness Attention mechanism Semantic segmentation Patch-based attack
ISSN号0920-5691
DOI10.1007/s11263-024-02120-9
英文摘要The attention mechanism has been proven effective on various visual tasks in recent years. In the semantic segmentation task, the attention mechanism is applied in various methods, including the case of both convolution neural networks and vision transformer as backbones. However, we observe that the attention mechanism is vulnerable to patch-based adversarial attacks. Through the analysis of the effective receptive field, we attribute it to the fact that the wide receptive field brought by global attention may lead to the spread of the adversarial patch. To address this issue, in this paper, we propose a robust attention mechanism (RAM) to improve the robustness of the semantic segmentation model, which can notably relieve the vulnerability against patch-based attacks. Compared to the vallina attention mechanism, RAM introduces two novel modules called max attention suppression and random attention dropout, both of which aim to refine the attention matrix and limit the influence of a single adversarial patch on the semantic segmentation results of other positions. Extensive experiments demonstrate the effectiveness of our RAM to improve the robustness of semantic segmentation models against various patch-based attack methods under different attack settings.
资助项目National Key R &D Program of China ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB0680000] ; Beijing Nova Program[20230484368] ; National Natural Science Foundation of China[62176251] ; Youth Innovation Promotion Association CAS ; [2021YFC3310100]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001240467000001
出版者SPRINGER
源URL[http://119.78.100.204/handle/2XEOYT63/40032]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Zhang, Jie
作者单位1.Chinese Acad Sci, Key Lab AI Safety, Beijing 100190, Peoples R China
2.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China
3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714		 Yuan, Zheng,Zhang, Jie,Wang, Yude,et al. Towards Robust Semantic Segmentation against Patch-Based Attack via Attention Refinement[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2024:23.
APA Yuan, Zheng,Zhang, Jie,Wang, Yude,Shan, Shiguang,&Chen, Xilin.(2024).Towards Robust Semantic Segmentation against Patch-Based Attack via Attention Refinement.INTERNATIONAL JOURNAL OF COMPUTER VISION,23.
MLA Yuan, Zheng,et al."Towards Robust Semantic Segmentation against Patch-Based Attack via Attention Refinement".INTERNATIONAL JOURNAL OF COMPUTER VISION (2024):23.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。