Exploratory adversarial attacks on graph neural networks

Xixun Lin, Chuan Zhou, Hong Yang, Jia Wu, Haibo Wang, Yanan Cao, Bin Wang

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

1 Citation (Scopus)


Graph neural networks (GNNs) have been successfully used to analyze non-Euclidean network data. Recently, there emerge a number of works to investigate the robustness of GNNs by adding adversarial noises into the graph topology, where gradient-based attacks are widely studied due to their inherent efficiency and high effectiveness. However, the gradient-based attacks often lead to sub-optimal results due to the discrete structure of graph data. To this end, we design a novel exploratory adversarial attack (termed as EpoAtk) to boost the gradient-based perturbations on graphs. The exploratory strategy in EpoAtk includes three phases, generation, evaluation and recombination, with the goal of sidesteping the possible misinformation that the maximal gradient provides. In experiments, EpoAtk is evaluated on benchmark datasets for the task of semi-supervised node classification in different attack settings. Experimental results demonstrate that the proposed method significantly outperforms the state-of-the-art attacks with the same attack budgets.
Original languageEnglish
Title of host publicationProceedings - 20th IEEE International Conference on Data Mining, ICDM 2020
EditorsClaudia Plant, Haixun Wang, Alfredo Cuzzocrea, Carlo Zaniolo, Xindong Wu
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages6
ISBN (Electronic)9781728183169
Publication statusPublished - 2020
Event20th IEEE International Conference on Data Mining, ICDM 2020 - Virtual, Sorrento, Italy
Duration: 17 Nov 202020 Nov 2020

Publication series

NameProceedings - IEEE International Conference on Data Mining, ICDM
ISSN (Print)1550-4786


Conference20th IEEE International Conference on Data Mining, ICDM 2020
CityVirtual, Sorrento


  • Gradient-based attacks
  • Graph neural networks
  • Maximal gradient
  • Semi-supervised node classification

Fingerprint Dive into the research topics of 'Exploratory adversarial attacks on graph neural networks'. Together they form a unique fingerprint.

Cite this