Link-Backdoor: Backdoor Attack on Link Prediction via Node Injection

被引:4
|
作者
Zheng, Haibin [1 ,2 ]
Xiong, Haiyang [2 ]
Ma, Haonan [2 ]
Huang, Guohan [2 ]
Chen, Jinyin [1 ,2 ]
机构
[1] Zhejiang Univ Technol, Inst Cyberspace Secur, Hangzhou 310023, Peoples R China
[2] Zhejiang Univ Technol, Coll Informat Engn, Hangzhou 310023, Peoples R China
关键词
Backdoor attack; defense; gradient information; link prediction; node injection;
D O I
10.1109/TCSS.2023.3260833
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Link prediction, inferring the undiscovered or potential links of the graph, is widely applied in the real-world. By facilitating labeled links of the graph as the training data, numerous deep learning based link prediction methods have been studied, which have dominant prediction accuracy compared with non-deep methods. However,the threats of maliciously crafted training graph will leave a specific backdoor in the deep model, thus when some specific examples are fed into the model, it will make wrong prediction, defined as backdoor attack. It is an important aspect that has been overlooked in the current literature. In this paper, we prompt the concept of backdoor attack on link prediction, and propose Link-Backdoor to reveal the training vulnerability of the existing link prediction methods. Specifically, the Link-Backdoor combines the fake nodes with the nodes of the target link to form a trigger. Moreover, it optimizes the trigger by the gradient information from the target model. Consequently, the link prediction model trained on the backdoored dataset will predict the link with trigger to the target state. Extensive experiments on five benchmark datasets and five well-performing link prediction models demonstrate that the Link-Backdoor achieves the state-of-the-art attack success rate under both white-box (i.e., available of the target model parameter)and black-box (i.e., unavailable of the target model parameter) scenarios. Additionally, we testify the attack under defensive circumstance, and the results indicate that the Link-Backdoor still can construct successful attack on the well-performing link prediction methods. The code and data are available at https://github.com/Seaocn/Link-Backdoor.
引用
收藏
页码:1816 / 1831
页数:16
相关论文
共 50 条
  • [11] Federated Learning Backdoor Attack Based on Frequency Domain Injection
    Liu, Jiawang
    Peng, Changgen
    Tan, Weijie
    Shi, Chenghui
    ENTROPY, 2024, 26 (02)
  • [12] A stealthy and robust backdoor attack via frequency domain transform
    Hou, Ruitao
    Huang, Teng
    Yan, Hongyang
    Ke, Lishan
    Tang, Weixuan
    WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS, 2023, 26 (05): : 2767 - 2783
  • [13] Feature-Based Graph Backdoor Attack in the Node Classification Task
    Chen, Yang
    Ye, Zhonglin
    Zhao, Haixing
    Wang, Ying
    INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, 2023, 2023
  • [14] TridentShell: An enhanced covert and scalable backdoor injection attack on web applications☆
    Yu, Xiaobo
    Meng, Weizhi
    Liu, Yining
    Zhou, Fei
    JOURNAL OF NETWORK AND COMPUTER APPLICATIONS, 2024, 223
  • [15] A stealthy and robust backdoor attack via frequency domain transform
    Ruitao Hou
    Teng Huang
    Hongyang Yan
    Lishan Ke
    Weixuan Tang
    World Wide Web, 2023, 26 : 2767 - 2783
  • [16] Link Prediction Adversarial Attack Via Iterative Gradient Attack
    Chen, Jinyin
    Lin, Xiang
    Shi, Ziqiang
    Liu, Yi
    IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS, 2020, 7 (04) : 1081 - 1094
  • [17] TridentShell: An enhanced covert and scalable backdoor injection attack on web applications
    Yu, Xiaobo
    Meng, Weizhi
    Liu, Yining
    Zhou, Fei
    Journal of Network and Computer Applications, 2024, 223
  • [18] A Clean-Label Graph Backdoor Attack Method in Node Classification Task
    Xing, Xiaogang
    Xu, Ming
    Bai, Yujing
    Yang, Dongdong
    KNOWLEDGE-BASED SYSTEMS, 2024, 304
  • [19] RF Domain Backdoor Attack on Signal Classification via Stealthy Trigger
    Tang, Zijie
    Zhao, Tianming
    Zhang, Tianfang
    Phan, Huy
    Wang, Yan
    Shi, Cong
    Yuan, Bo
    Chen, Yingying
    IEEE TRANSACTIONS ON MOBILE COMPUTING, 2024, 23 (12) : 11765 - 11780
  • [20] Spatialspectral-Backdoor: Realizing backdoor attack for deep neural networks in brain-computer interface via EEG characteristics
    Li, Fumin
    Huang, Mengjie
    You, Wenlong
    Zhu, Longsheng
    Cheng, Hanjing
    Yang, Rui
    NEUROCOMPUTING, 2025, 616