Graph Adversarial Immunization for Certifiable Robustness

doi:10.1109/TKDE.2023.3311105

	Graph Adversarial Immunization for Certifiable Robustness
	Tao, Shuchang 1,2; Cao, Qi 1,2; Shen, Huawei 1,2; Wu, Yunfan 1,2; Hou, Liang 1,2; Cheng, Xueqi 3
	2024-04-01
发表期刊	IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
ISSN	1041-4347
卷号	36 期号:4 页码:1597-1610
摘要	Despite achieving great success, graph neural networks (GNNs) are vulnerable to adversarial attacks. Existing defenses focus on developing adversarial training or model modification. In this paper, we propose and formulate graph adversarial immunization, i.e., vaccinating part of graph structure to improve certifiable robustness of graph against any admissible adversarial attack. We first propose edge-level immunization to vaccinate node pairs. Unfortunately, such edge-level immunization cannot defend against emerging node injection attacks, since it only immunizes existing node pairs. To this end, we further propose node-level immunization. To avoid computationally intensive combinatorial optimization associated with adversarial immunization, we develop AdvImmune-Edge and AdvImmune-Node algorithms to effectively obtain the immune node pairs or nodes. Extensive experiments demonstrate the superiority of AdvImmune methods. In particular, AdvImmune-Node remarkably improves the ratio of robust nodes by 79$\%$%, 294$\%$%, and 100$\%$%, after immunizing only 5$\%$% of nodes. Furthermore, AdvImmune methods show excellent defensive performance against various attacks, outperforming state-of-the-art defenses. To the best of our knowledge, this is the first attempt to improve certifiable robustness from graph data perspective without losing performance on clean graphs, providing new insights into graph adversarial learning.
关键词	Adversarial attack adversarial immunization certifiable robustness graph neural networks node classification
DOI	10.1109/TKDE.2023.3311105
收录类别	SCI
语种	英语
资助项目	National Key Ramp;D Program of China
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Information Systems ; Engineering, Electrical & Electronic
WOS记录号	WOS:001181467200023
出版者	IEEE COMPUTER SOC
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/38735
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, Inst Comp Technol, Data Intelligence Syst Res Ctr, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, CAS Key Lab Network Data Sci & Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Tao, Shuchang,Cao, Qi,Shen, Huawei,et al. Graph Adversarial Immunization for Certifiable Robustness[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2024,36(4):1597-1610.
APA	Tao, Shuchang,Cao, Qi,Shen, Huawei,Wu, Yunfan,Hou, Liang,&Cheng, Xueqi.(2024).Graph Adversarial Immunization for Certifiable Robustness.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,36(4),1597-1610.
MLA	Tao, Shuchang,et al."Graph Adversarial Immunization for Certifiable Robustness".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 36.4(2024):1597-1610.