Print Email Facebook Twitter Poster Title Poster: Clean-label Backdoor Attack on Graph Neural Networks Author Xu, J. (TU Delft Cyber Security) Picek, S. (TU Delft Cyber Security; Radboud Universiteit Nijmegen) Date 2022 Abstract Graph Neural Networks (GNNs) have achieved impressive results in various graph learning tasks. They have found their way into many applications, such as fraud detection, molecular property prediction, or knowledge graph reasoning. However, GNNs have been recently demonstrated to be vulnerable to backdoor attacks. In this work, we explore a new kind of backdoor attack, i.e., a clean-label backdoor attack, on GNNs. Unlike prior backdoor attacks on GNNs in which the adversary can introduce arbitrary, often clearly mislabeled, inputs to the training set, in a clean-label backdoor attack, the resulting poisoned inputs appear to be consistent with their label and thus are less likely to be filtered as outliers. The initial experimental results illustrate that the adversary can achieve a high attack success rate (up to 98.47%) with a clean-label backdoor attack on GNNs for the graph classification task. We hope our work will raise awareness of this attack and inspire novel defenses against it. Subject backdoor attacksgraph classificationgraph neural networks To reference this document use: http://resolver.tudelft.nl/uuid:1e074235-2ccf-470a-9806-2371e918ca39 DOI https://doi.org/10.1145/3548606.3563531 Publisher Association for Computing Machinery (ACM) ISBN 9781450394505 Source CCS 2022 - Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security Event 28th ACM SIGSAC Conference on Computer and Communications Security, CCS 2022, 2022-11-07 → 2022-11-11, Los Angeles, United States Series Proceedings of the ACM Conference on Computer and Communications Security, 1543-7221 Bibliographical note . Part of collection Institutional Repository Document type conference paper Rights © 2022 J. Xu, S. Picek Files PDF 3548606.3563531.pdf 1019.9 KB Close viewer /islandora/object/uuid:1e074235-2ccf-470a-9806-2371e918ca39/datastream/OBJ/view