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
Adversarial camouflage for node injection attack on graphs

文献类型：期刊论文

作者Tao, Shuchang1,2; Cao, Qi1; Shen, Huawei1,2; Wu, Yunfan1,2; Hou, Liang1,2; Sun, Fei1; Cheng, Xueqi2,3
刊名INFORMATION SCIENCES
出版日期2023-11-01
卷号649页码:14
ISSN号0020-0255
关键词Adversarial camouflage Node injection attack Adversarial attack Graph neural networks
DOI10.1016/j.ins.2023.119611
英文摘要Node injection attacks on Graph Neural Networks (GNNs) have received increasing attention recently, due to their ability to degrade GNN performance with high attack success rates. However, our study indicates that these attacks often fail in practical scenarios, since defense/detection methods can easily identify and remove the injected nodes. To address this, we devote to camouflage node injection attack, making injected nodes appear normal and imperceptible to defense/detection methods. Unfortunately, the non-Euclidean structure of graph data and the lack of intuitive prior present great challenges to the formalization, implementation, and evaluation of camouflage. In this paper, we first propose and define camouflage as distribution similarity between ego networks of injected nodes and normal nodes. Then for implementation, we propose an adversarial CAmouflage framework for Node injection Attack, namely CANA, to improve attack performance under defense/detection methods in practical scenarios. A novel camouflage metric is further designed under the guide of distribution similarity. Extensive experiments demonstrate that CANA can significantly improve the attack performance under defense/detection methods with higher camouflage or imperceptibility. This work urges us to raise awareness of the security vulnerabilities of GNNs in practical applications.
资助项目National Key Ramp;D Program of China[2022YFB3103700] ; National Key Ramp;D Program of China[2022YFB3103701] ; National Natural Science Foundation of China[62102402] ; National Natural Science Foundation of China[62272125] ; National Natural Science Foundation of China[U21B2046] ; Beijing Academy of Artificial Intelligence (BAAI)
WOS研究方向Computer Science
语种英语
出版者ELSEVIER SCIENCE INC
WOS记录号WOS:001073549100001
源URL[http://119.78.100.204/handle/2XEOYT63/21155]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Cao, Qi; Shen, Huawei
作者单位1.Chinese Acad Sci, Data Intelligence Syst Res Ctr, Inst Comp Technol, Beijing, Peoples R China
2.Univ Chinese Acad Sci, Beijing, Peoples R China
3.Chinese Acad Sci, CAS Key Lab Network Data Sci & Technol, Inst Comp Technol, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Tao, Shuchang,Cao, Qi,Shen, Huawei,et al. Adversarial camouflage for node injection attack on graphs[J]. INFORMATION SCIENCES,2023,649:14.
APA Tao, Shuchang.,Cao, Qi.,Shen, Huawei.,Wu, Yunfan.,Hou, Liang.,...&Cheng, Xueqi.(2023).Adversarial camouflage for node injection attack on graphs.INFORMATION SCIENCES,649,14.
MLA Tao, Shuchang,et al."Adversarial camouflage for node injection attack on graphs".INFORMATION SCIENCES 649(2023):14.

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。