Print Email Facebook Twitter Rethinking the Trigger-injecting Position in Graph Backdoor Attack Title Rethinking the Trigger-injecting Position in Graph Backdoor Attack Author Xu, J. (TU Delft Cyber Security) Abad, Gorka (Radboud Universiteit Nijmegen; Ikerlan research centre) Picek, S. (TU Delft Cyber Security; Radboud Universiteit Nijmegen) Date 2023 Abstract Backdoor attacks have been demonstrated as a security threat for machine learning models. Traditional backdoor attacks intend to inject backdoor functionality into the model such that the backdoored model will perform abnormally on inputs with predefined backdoor triggers and still retain state-of-the-art performance on the clean inputs. While there are already some works on backdoor attacks on Graph Neural Networks (GNNs), the backdoor trigger in the graph domain is mostly injected into random positions of the sample. There is no work analyzing and explaining the backdoor attack performance when injecting triggers into the most important or least important area in the sample, which we refer to as trigger-injecting strategies MIAS and LIAS, respectively. Our results show that, generally, LIAS performs better, and the differences between the LIAS and MIAS performance can be significant. Furthermore, we explain these two strategies’ similar (better) attack performance through explanation techniques, which results in a further understanding of backdoor attacks in GNNs. Subject backdoor attacktrigger-injecting positiongraph neural networks To reference this document use: http://resolver.tudelft.nl/uuid:69e1c1f3-9049-432f-acb1-e40b8b65184f DOI https://doi.org/10.1109/IJCNN54540.2023.10191949 Publisher IEEE, Piscataway Embargo date 2024-02-02 ISBN 978-1-6654-8868-6 Source Proceedings of the 2023 International Joint Conference on Neural Networks (IJCNN) Event 2023 International Joint Conference on Neural Networks (IJCNN), 2023-06-18 → 2023-06-23, Gold Coast, Australia Series Proceedings of the International Joint Conference on Neural Networks, 2023-June Bibliographical note Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type conference paper Rights © 2023 J. Xu, Gorka Abad, S. Picek Files PDF Rethinking_the_Trigger_in ... Attack.pdf 1.39 MB Close viewer /islandora/object/uuid:69e1c1f3-9049-432f-acb1-e40b8b65184f/datastream/OBJ/view