Explainability-based Backdoor Attacks against Graph Neural Networks

Jing Xu, Minhui Xue, Stjepan Picek

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

3 Citations (Scopus)
27 Downloads (Pure)

Abstract

Backdoor attacks represent a serious threat to neural network models. A backdoored model will misclassify the trigger-embedded inputs into an attacker-chosen target label while performing normally on other benign inputs. There are already numerous works on backdoor attacks on neural networks, but only a few works consider graph neural networks (GNNs). As such, there is no intensive research on explaining the impact of trigger injecting position on the performance of backdoor attacks on GNNs. To bridge this gap, we conduct an experimental investigation on the performance of backdoor attacks on GNNs. We apply two powerful GNN explainability approaches to select the optimal trigger injecting position to achieve two attacker objectives - high attack success rate and low clean accuracy drop. Our empirical results on benchmark datasets and state-of-the-art neural network models demonstrate the proposed method's effectiveness in selecting trigger injecting position for backdoor attacks on GNNs. For instance, on the node classification task, the backdoor attack with trigger injecting position selected by GraphLIME reaches over 84% attack success rate with less than 2.5% accuracy drop.

Original languageEnglish
Title of host publicationWiseML 2021
Subtitle of host publicationProceedings of the 3rd ACM Workshop on Wireless Security and Machine Learning
Place of PublicationNew York
PublisherAssociation for Computing Machinery (ACM)
Pages31-36
Number of pages6
ISBN (Electronic)978-1-4503-8561-9
DOIs
Publication statusPublished - 2021
Event3rd ACM Workshop on Wireless Security and Machine Learning, WiseML 2021 - Virtual, Online, United Arab Emirates
Duration: 2 Jul 20212 Jul 2021

Conference

Conference3rd ACM Workshop on Wireless Security and Machine Learning, WiseML 2021
Country/TerritoryUnited Arab Emirates
CityVirtual, Online
Period2/07/212/07/21

Keywords

  • backdoor attacks
  • explainability
  • graph neural networks

Fingerprint

Dive into the research topics of 'Explainability-based Backdoor Attacks against Graph Neural Networks'. Together they form a unique fingerprint.

Cite this