Unnoticeable Backdoor Attacks on Graph Neural Networks

Enyan Dai, Minhua Lin, Xiang Zhang, Suhang Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations


Graph Neural Networks (GNNs) have achieved promising results in various tasks such as node classification and graph classification. Recent studies find that GNNs are vulnerable to adversarial attacks. However, effective backdoor attacks on graphs are still an open problem. In particular, backdoor attack poisons the graph by attaching triggers and the target class label to a set of nodes in the training graph. The backdoored GNNs trained on the poisoned graph will then be misled to predict test nodes to target class once attached with triggers. Though there are some initial efforts in graph backdoor attacks, our empirical analysis shows that they may require a large attack budget for effective backdoor attacks and the injected triggers can be easily detected and pruned. Therefore, in this paper, we study a novel problem of unnoticeable graph backdoor attacks with limited attack budget. To fully utilize the attack budget, we propose to deliberately select the nodes to inject triggers and target class labels in the poisoning phase. An adaptive trigger generator is deployed to obtain effective triggers that are difficult to be noticed. Extensive experiments on real-world datasets against various defense strategies demonstrate the effectiveness of our proposed method in conducting effective unnoticeable backdoor attacks.

Original languageEnglish (US)
Title of host publicationACM Web Conference 2023 - Proceedings of the World Wide Web Conference, WWW 2023
PublisherAssociation for Computing Machinery, Inc
Number of pages11
ISBN (Electronic)9781450394161
StatePublished - Apr 30 2023
Event2023 World Wide Web Conference, WWW 2023 - Austin, United States
Duration: Apr 30 2023May 4 2023

Publication series

NameACM Web Conference 2023 - Proceedings of the World Wide Web Conference, WWW 2023


Conference2023 World Wide Web Conference, WWW 2023
Country/TerritoryUnited States

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Software

Cite this