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
  • [31] Audio-domain Position-independent Backdoor Attack via Unnoticeable Triggers
    Shi, Cong
    Zhang, Tianfang
    Li, Zhuohang
    Phan, Huy
    Zhao, Tianming
    Wang, Yan
    Liu, Jian
    Yuan, Bo
    Chen, Yingying
    PROCEEDINGS OF THE 2022 THE 28TH ANNUAL INTERNATIONAL CONFERENCE ON MOBILE COMPUTING AND NETWORKING, ACM MOBICOM 2022, 2022, : 583 - 595
  • [32] A New Link Prediction Algorithm: Node Link Strength Algorithm
    Yin Guisheng
    Yin Wansi
    Dong Yuxin
    2014 IEEE SYMPOSIUM ON COMPUTER APPLICATIONS AND COMMUNICATIONS (SCAC), 2014, : 5 - 9
  • [33] iBA: Backdoor Attack on 3D Point Cloud via Reconstructing Itself
    Bian, Yuhao
    Tian, Shengjing
    Liu, Xiuping
    IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2024, 19 : 7994 - 8008
  • [34] UltraBD: Backdoor Attack against Automatic Speaker Verification Systems via Adversarial Ultrasound
    Ze, Junning
    Li, Xinfeng
    Cheng, Yushi
    Ji, Xiaoyu
    Xu, Wenyuan
    2022 IEEE 28TH INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED SYSTEMS, ICPADS, 2022, : 193 - 200
  • [35] A frequency-injection backdoor attack against DNN-Based finger vein verification
    Zhang, Huijie
    Sun, Weizhen
    Lv, Ling
    COMPUTERS & SECURITY, 2024, 144
  • [36] Link prediction based on node centrality
    Li, LanXi
    Liu, Xiangchun
    Chen, Ning
    Tian, Hui
    PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY AND ELECTRICAL ENGINEERING 2018 (ICITEE '18), 2018,
  • [37] Link prediction with node clustering coefficient
    Wu, Zhihao
    Lin, Youfang
    Wang, Jing
    Gregory, Steve
    PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2016, 452 : 1 - 8
  • [38] DeepPayload: Black-box Backdoor Attack on Deep Learning Models through Neural Payload Injection
    Li, Yuanchun
    Hua, Liayi
    Wang, Haoyu
    Chen, Chunyang
    Liu, Yunxin
    2021 IEEE/ACM 43RD INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING (ICSE 2021), 2021, : 263 - 274
  • [39] DeHiB: Deep Hidden Backdoor Attack on Semi-supervised Learning via Adversarial Perturbation
    Yan, Zhicong
    Li, Gaolei
    Tian, Yuan
    Wu, Jun
    Li, Shenghong
    Chen, Mingzhe
    Poor, H. Vincent
    THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 10585 - 10593
  • [40] Evolutionary Perturbation Attack on Temporal Link Prediction
    Zhang, Ting
    Lv, Laishui
    Bardou, Dalal
    JOURNAL OF THE PHYSICAL SOCIETY OF JAPAN, 2024, 93 (07)