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
  • [41] Heterogeneous Link Prediction via Mutual Information Maximization Between Node Pairs
    Lu, Yifan
    Liu, Zehao
    Gao, Mengzhou
    Jiao, Pengfei
    ARTIFICIAL INTELLIGENCE, CICAI 2023, PT I, 2024, 14473 : 460 - 470
  • [42] Temporal link prediction based on node dynamics
    Wu, Jiayun
    He, Langzhou
    Jia, Tao
    Tao, Li
    CHAOS SOLITONS & FRACTALS, 2023, 170
  • [43] General link prediction with influential node identification
    Wu, Jiehua
    Shen, Jing
    Zhou, Bei
    Zhang, Xiayan
    Huang, Bohuai
    PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2019, 523 : 996 - 1007
  • [44] Link Prediction via Matrix Factorization
    Menon, Aditya Krishna
    Elkan, Charles
    MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, PT II, 2011, 6912 : 437 - 452
  • [45] Link prediction via linear optimization
    Pech, Ratha
    Hao, Dong
    Lee, Yan-Li
    Yuan, Ye
    Zhou, Tao
    PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2019, 528
  • [46] Link prediction via significant influence
    Yang, Yujie
    Zhang, Jianhua
    Zhu, Xuzhen
    Tian, Lei
    PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2018, 492 : 1523 - 1530
  • [47] Link prediction via matrix completion
    Pech, Ratha
    Hao, Dong
    Pan, Liming
    Cheng, Hong
    Zhou, Tao
    EPL, 2017, 117 (03)
  • [48] Link Prediction via Factorization Machines
    Li, Lile
    Liu, Wei
    AI 2018: ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, 11320 : 681 - 691
  • [49] Leveraging Node Attributes for Link Prediction via Meta-path Based Proximity
    Feng, Xiaoyan
    Dai, Mingyang
    2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
  • [50] Blind Concealment from Reconstruction-based Attack Detectors for Industrial Control Systems via Backdoor Attacks
    Walita, Tim
    Erba, Alessandro
    Castellanos, John H.
    Tippenhauer, Nils Ole
    PROCEEDINGS OF THE 9TH ACM CYBER-PHYSICAL SYSTEM SECURITY WORKSHOP, CPSS 2023, 2023, : 36 - 47