research-article

Adversarial Attacks on Link Prediction Algorithms Based on Graph Neural Networks

Authors:

Baochun LiAuthors Info & Claims

ASIA CCS '20: Proceedings of the 15th ACM Asia Conference on Computer and Communications Security

Pages 370 - 380

https://doi.org/10.1145/3320269.3384750

Published: 05 October 2020 Publication History

Abstract

Link prediction is one of the fundamental problems for graph-structured data. However, a number of applications of link prediction, such as predicting commercial ties or memberships within a criminal organization, are adversarial, with another party aiming to minimize its effectiveness by manipulating observed information about the graph. In this paper, we focus on the feasibility of mounting adversarial attacks against link prediction algorithms based on graph neural networks. We first propose a greedy heuristic that exploits incremental computation to find attacks against a state-of-the-art link prediction algorithm, called SEAL. We then design an efficient variant of this algorithm that incorporates the link formation mechanism and Υ-decaying heuristic theory to design more effective adversarial attacks. We used real-world datasets and performed an extensive array of experiments to show that the performance of SEAL is negatively affected by a significant margin. More importantly, our experimental results have shown that our adversarial attacks mounted based on SEAL can be readily transferred to several existing link prediction heuristics in the literature.

References

[1]

Robert Ackland et al. 2005. Mapping the US Political Blogosphere: Are Conservative Bloggers More Prominent?. In BlogTalk Downunder 2005 Conference, Sydney. BlogTalk Downunder 2005 Conference, Sydney.

[2]

Lada A Adamic and Eytan Adar. 2003. Friends and Neighbors on the Web. Social Networks, Vol. 25, 3 (2003), 211--230.

[3]

Mohammad Al Hasan, Vineet Chaoji, Saeed Salem, and Mohammed Zaki. 2006. Link Prediction using Supervised Learning. In SDM06: Workshop on Link Analysis, Counter-Terrorism and Security.

[4]

Albert-László Barabási and Réka Albert. 1999. Emergence of Scaling in Random Networks. Science, Vol. 286, 5439 (1999), 509--512.

[5]

Vladimir Batagelj and Andrej Mrvar. 2006. http://vlado.fmf.unilj.si/pub/networks/data/

[6]

Sergey Brin and Lawrence Page. 1998. The Anatomy of a Large-Scale Hypertextual Web Search Engine. Computer Networks and ISDN Systems, Vol. 30, 1--7 (1998), 107--117.

Digital Library

[7]

Emrah Budur, Seungmin Lee, and Vein S Kong. 2015. Structural Analysis of Criminal Network and Predicting Hidden Links using Machine Learning. arXiv preprint arXiv:1507.05739 (2015).

[8]

Nicholas Carlini and David Wagner. 2017. Towards Evaluating the Robustness of Neural Networks. In Proc. IEEE Symposium on Security and Privacy (S&P 2017).

[9]

Nicholas Carlini and David Wagner. 2018. Audio Adversarial Examples: Targeted Attacks on Speech-to-Text. arXiv preprint arXiv:1801.01944 (2018).

[10]

Jinjin Chen, Ziqiang Shi, Yangyang Wu, Xuanheng Xu, and Haibin Zheng. 2018b. Link Prediction Adversarial Attack. arXiv preprint arXiv:1803.06373 (2018).

[11]

Pin-Yu Chen, Yash Sharma, Huan Zhang, Jinfeng Yi, and Cho-Jui Hsieh. 2018a. EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples. In Proc. AAAI Conference on Artificial Intelligence (AAAI 2018).

[12]

Yizheng Chen, Yacin Nadji, Athanasios Kountouras, Fabian Monrose, Roberto Perdisci, Manos Antonakakis, and Nikolaos Vasiloglou. 2017. Practical Attacks against Graph-Based Clustering. In Proc. ACM SIGSAC Conference on Computer and Communications Security (CCS 2017).

Digital Library

[13]

Hanjun Dai, Hui Li, Tian Tian, Xin Huang, Lin Wang, Jun Zhu, and Le Song. 2018. Adversarial Attack on Graph Structured Data. In Proc. International Conference on Machine Learning (ICML 2018).

[14]

Yuxiao Dong, Jie Tang, Sen Wu, Jilei Tian, Nitesh V Chawla, Jinghai Rao, and Huanhuan Cao. 2012. Link Prediction and Recommendation across Heterogeneous Social Networks. In Proc. IEEE International Conference on Data Mining (ICDM 2012). 181--190.

Digital Library

[15]

Kathrin Grosse, Nicolas Papernot, Praveen Manoharan, Michael Backes, and Patrick McDaniel. 2017. Adversarial Examples for Malware Detection. In Proc. European Symposium on Research in Computer Security (ESORICS 2017). Springer.

[16]

Ling Huang, Anthony D Joseph, Blaine Nelson, Benjamin IP Rubinstein, and JD Tygar. 2011. Adversarial Machine Learning. In Proc. ACM Workshop on Security and Artificial Intelligence.

Digital Library

[17]

Glen Jeh and Jennifer Widom. 2002. SimRank: A Measure of Structural-Context Similarity. In Proc. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2002). 538--543.

Digital Library

[18]

Harini Kannan, Alexey Kurakin, and Ian Goodfellow. 2018. Adversarial Logit Pairing. arXiv preprint arXiv:1803.06373 (2018).

[19]

Leo Katz. 1953. A New Status Index Derived from Sociometric Analysis. Psychometrika, Vol. 18, 1 (1953), 39--43.

[20]

David Liben-Nowell and Jon Kleinberg. 2007. The Link-Prediction Problem for Social Networks. Journal of the American Society for Information Science and Technology, Vol. 58, 7 (2007), 1019--1031.

Digital Library

[21]

Yanpei Liu, Xinyun Chen, Chang Liu, and Dawn Song. 2017. Delving into Transferable Adversarial Examples and Black-Box Attacks. In Proc. International Conference on Learning Representation (ICLR 2017).

[22]

Linyuan Lü and Tao Zhou. 2011. Link Prediction in Complex Networks: A Survey. Physica A: Statistical Mechanics and Its Applications, Vol. 390, 6 (2011), 1150--1170.

[23]

Yacin Nadji, Manos Antonakakis, Roberto Perdisci, and Wenke Lee. 2013. Connected Colors: Unveiling the Structure of Criminal Networks. In Proc. International Workshop on Recent Advances in Intrusion Detection. Springer.

Digital Library

[24]

Mark EJ Newman. 2006. Finding Community Structure in Networks using the Eigenvectors of Matrices. Physical Review E, Vol. 74, 3 (2006), 036104.

[25]

Joshua O'Madadhain, Jon Hutchins, and Padhraic Smyth. 2005. Prediction and Ranking Algorithms for Event-Based Network Data. ACM SIGKDD Explorations Newsletter, Vol. 7, 2 (2005), 23--30.

Digital Library

[26]

Nicolas Papernot, Patrick McDaniel, and Ian Goodfellow. 2016. Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples. arXiv preprint arXiv:1605.07277 (2016).

[27]

Nicolas Papernot, Patrick McDaniel, Ian Goodfellow, Somesh Jha, Z Berkay Celik, and Ananthram Swami. 2017. Practical Black-Box Attacks against Machine Learning. In Proc. ACM on Asia Conference on Computer and Communications Security (AsiaCCS 2017). ACM, 506--519.

Digital Library

[28]

Nino Shervashidze, Pascal Schweitzer, Erik Jan van Leeuwen, Kurt Mehlhorn, and Karsten M Borgwardt. 2011. Weisfeiler-Lehman Graph Kernels. Journal of Machine Learning Research, Vol. 12, Sep (2011), 2539--2561.

Digital Library

[29]

Florian Tramèr, Nicolas Papernot, Ian Goodfellow, Dan Boneh, and Patrick McDaniel. 2017. The Space of Transferable Adversarial Examples. arXiv preprint arXiv:1704.03453 (2017).

[30]

Binghui Wang and Neil Zhenqiang Gong. 2019. Attacking Graph-based Classification via Manipulating the Graph Structure. In Proc. ACM SIGSAC Conference on Computer and Communications Security (CCS 2019).

Digital Library

[31]

Hao Wang, Xingjian Shi, and Dit-Yan Yeung. 2017. Relational Deep Learning: A Deep Latent Variable Model for Link Prediction. In Proc. AAAI Conference on Artificial Intelligence.

[32]

Duncan J Watts and Steven H Strogatz. 1998. Collective Dynamics of “Small-World” Networks. Nature, Vol. 393, 6684 (1998), 440.

[33]

Muhan Zhang and Yixin Chen. 2017. Weisfeiler-Lehman Neural Machine for Link Prediction. In Proc. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2017).

Digital Library

[34]

Muhan Zhang and Yixin Chen. 2018. Link Prediction Based on Graph Neural Networks. In Proc. International Conference on Neural Information Processing Systems (NeurIPS 2018).

[35]

Muhan Zhang, Zhicheng Cui, Marion Neumann, and Yixin Chen. 2018. An End-to-End Deep Learning Architecture for Graph Classification. In Proc. AAAI Conference on Artificial Intelligence (AAAI 2018).

[36]

Tao Zhou, Linyuan Lü, and Yi-Cheng Zhang. 2009. Predicting Missing Links via Local Information. The European Physical Journal B, Vol. 71, 4 (2009), 623--630.

[37]

Daniel Zugner, Amir Akbarnejad, and Stephan Gunnemann. 2018. Adversarial Attacks on Neural Networks for Graph Data. In Proc. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2018).

Digital Library

[38]

Daniel Zugner and Stephan Gunnemann. 2019. Adversarial Attacks on Graph Neural Networks via Meta Learning. In Proc. International Conference on Learning Representation (ICLR 2019).

Cited By

Tang RYong ZMei YLi XLi JDing JMo X(2024)Degrading the accuracy of interlayer link prediction: A method based on the analysis of node importanceInternational Journal of Modern Physics C10.1142/S012918312442004XOnline publication date: 21-Jun-2024
https://doi.org/10.1142/S012918312442004X
Chen JMa MMa HZheng HZhang J(2024)An Empirical Evaluation of the Data Leakage in Federated Graph LearningIEEE Transactions on Network Science and Engineering10.1109/TNSE.2023.332635911:2(1605-1618)Online publication date: Mar-2024
https://doi.org/10.1109/TNSE.2023.3326359
Trappolini GMaiorca VSeverino SRodolà ESilvestri FTolomei G(2024)Sparse Vicious Attacks on Graph Neural NetworksIEEE Transactions on Artificial Intelligence10.1109/TAI.2023.33193065:5(2293-2303)Online publication date: May-2024
https://doi.org/10.1109/TAI.2023.3319306
Show More Cited By

Index Terms

Adversarial Attacks on Link Prediction Algorithms Based on Graph Neural Networks
1. Security and privacy
  1. Network security

Recommendations

Graph Structure Learning for Robust Graph Neural Networks
KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining

Graph Neural Networks (GNNs) are powerful tools in representation learning for graphs. However, recent studies show that GNNs are vulnerable to carefully-crafted perturbations, called adversarial attacks. Adversarial attacks can easily fool GNNs in ...
Adversarial Attacks on Graph Neural Networks: Perturbations and their Patterns
Special Issue on KDD 2018, Regular Papers and Survey Paper

Deep learning models for graphs have achieved strong performance for the task of node classification. Despite their proliferation, little is known about their robustness to adversarial attacks. Yet, in domains where they are likely to be used, e.g., the ...
Structack: Structure-based Adversarial Attacks on Graph Neural Networks
HT '21: Proceedings of the 32nd ACM Conference on Hypertext and Social Media

Recent work has shown that graph neural networks (GNNs) are vulnerable to adversarial attacks on graph data. Common attack approaches are typically informed, i.e. they have access to information about node attributes such as labels and feature vectors. ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

ASIA CCS '20: Proceedings of the 15th ACM Asia Conference on Computer and Communications Security

October 2020

957 pages

ISBN:9781450367509

DOI:10.1145/3320269

General Chairs:
Hung-Min Sun
National Tsing Hua University, Taiwan
,
Shiuhpyng Shieh
National Chiao Tung University, Taiwan
,
Program Chairs:
Guofei Gu
Texas A&M University, USA
,
Giuseppe Ateniese
Stevens Institute of Technology, USA

Copyright © 2020 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGSAC: ACM Special Interest Group on Security, Audit, and Control

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 05 October 2020

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

This research was supported in part by the NSERC Discovery Research Program.

Conference

ASIA CCS '20

Sponsor:

SIGSAC

ASIA CCS '20: The 15th ACM Asia Conference on Computer and Communications Security

October 5 - 9, 2020

Taipei, Taiwan

Acceptance Rates

Overall Acceptance Rate 418 of 2,322 submissions, 18%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

19
Total Citations
View Citations
549
Total Downloads

Downloads (Last 12 months)104
Downloads (Last 6 weeks)7

Reflects downloads up to 14 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Tang RYong ZMei YLi XLi JDing JMo X(2024)Degrading the accuracy of interlayer link prediction: A method based on the analysis of node importanceInternational Journal of Modern Physics C10.1142/S012918312442004XOnline publication date: 21-Jun-2024
https://doi.org/10.1142/S012918312442004X
Chen JMa MMa HZheng HZhang J(2024)An Empirical Evaluation of the Data Leakage in Federated Graph LearningIEEE Transactions on Network Science and Engineering10.1109/TNSE.2023.332635911:2(1605-1618)Online publication date: Mar-2024
https://doi.org/10.1109/TNSE.2023.3326359
Trappolini GMaiorca VSeverino SRodolà ESilvestri FTolomei G(2024)Sparse Vicious Attacks on Graph Neural NetworksIEEE Transactions on Artificial Intelligence10.1109/TAI.2023.33193065:5(2293-2303)Online publication date: May-2024
https://doi.org/10.1109/TAI.2023.3319306
Tian BZang LFu HHan JHu S(2024)Towards More Effective and Transferable Poisoning Attacks against Link Prediction on Graphs2024 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD)10.1109/CSCWD61410.2024.10580418(525-530)Online publication date: 8-May-2024
https://doi.org/10.1109/CSCWD61410.2024.10580418
Xu XHao QYang ZLi BLiebovitz DWang GGunter CCalandrino JTroncoso C(2023)How to cover up anomalous accesses to electronic health recordsProceedings of the 32nd USENIX Conference on Security Symposium10.5555/3620237.3620251(229-246)Online publication date: 9-Aug-2023
https://dl.acm.org/doi/10.5555/3620237.3620251
Romero Hung JLi CWang TGuo JWang PShao CWang JShi GLiu XWu H(2023)DRAGON: Dynamic Recurrent Accelerator for Graph Online ConvolutionACM Transactions on Design Automation of Electronic Systems10.1145/352412428:1(1-27)Online publication date: 20-Jan-2023
https://dl.acm.org/doi/10.1145/3524124
Yin XLin WSun KWei CChen Y(2023) A 2 S 2 -GNN: Rigging GNN-Based Social Status by Adversarial Attacks in Signed Social Networks IEEE Transactions on Information Forensics and Security10.1109/TIFS.2022.321934218(206-220)Online publication date: 2023
https://doi.org/10.1109/TIFS.2022.3219342
Miao ZZhuo XWu GBu C(2023)Semantic-Reconstructed Graph Transformer Network for Event Detection2023 International Joint Conference on Neural Networks (IJCNN)10.1109/IJCNN54540.2023.10191893(1-8)Online publication date: 18-Jun-2023
https://doi.org/10.1109/IJCNN54540.2023.10191893
Wu TCui CZhao ZXian XTian KCao X(2023)Rethinking the Robustness of Graph Neural NetworksBig Data and Social Computing10.1007/978-981-99-3925-1_23(346-361)Online publication date: 30-Jun-2023
https://doi.org/10.1007/978-981-99-3925-1_23
Duan TWang WLi XZhu YHuang M(2023)Towards Intelligent UAV Swarm Mission Planning Methodology and AlgorithmsProceedings of 2022 International Conference on Autonomous Unmanned Systems (ICAUS 2022)10.1007/978-981-99-0479-2_18(190-202)Online publication date: 10-Mar-2023
https://doi.org/10.1007/978-981-99-0479-2_18
Show More Cited By

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents