مؤتمر
Adapting Membership Inference Attacks to GNN for Graph Classification: Approaches and Implications
| العنوان: | Adapting Membership Inference Attacks to GNN for Graph Classification: Approaches and Implications |
|---|---|
| المؤلفون: | Wu, Bang, Yang, Xiangwen, Pan, Shirui, Yuan, Xingliang |
| بيانات النشر: | IEEE |
| سنة النشر: | 2021 |
| المجموعة: | Griffith University: Griffith Research Online |
| مصطلحات موضوعية: | Neural networks, Computer Science, Artificial Intelligence, Information Systems, Graph Classification, Graph Neural Networks |
| جغرافية الموضوع: | Auckland, New Zealand |
| الوقت: | 2021-12-07 to 2021-12-10 |
| الوصف: | In light of the wide application of Graph Neural Networks (GNNs), Membership Inference Attack (MIA) against GNNs raises severe privacy concerns, where training data can be leaked from trained GNN models. However, prior studies focus on inferring the membership of only the components in a graph, e.g., an individual node or edge. In this paper, we take the first step in MIA against GNNs for graph-level classification. Our objective is to infer whether a graph sample has been used for training a GNN model. We present and implement two types of attacks, i.e., training-based attacks and threshold-based attacks from different adversarial capabilities. We perform comprehensive experiments to evaluate our attacks in seven real-world datasets using five representative GNN models. Both our attacks are shown effective and can achieve high performance, i.e., reaching over 0.7 attack F1 scores in most cases1. Our findings also confirm that, unlike the node-level classifier, MIAs on graph-level classification tasks are more co-related with the overfitting level of GNNs rather than the statistic property of their training graphs. ; Full Text |
| نوع الوثيقة: | conference object |
| اللغة: | English |
| ردمك: | 978-1-66542-398-4 1-66542-398-6 |
| تدمد: | 1550-4786 |
| العلاقة: | 2021 IEEE International Conference on Data Mining (ICDM); 21st IEEE International Conference on Data Mining (IEEE ICDM); Wu, B; Yang, X; Pan, S; Yuan, X, Adapting Membership Inference Attacks to GNN for Graph Classification: Approaches and Implications, 2021 IEEE International Conference on Data Mining (ICDM), 2021, pp. 1421-1426; http://hdl.handle.net/10072/416704Test |
| DOI: | 10.1109/ICDM51629.2021.00182 |
| الإتاحة: | https://doi.org/10.1109/ICDM51629.2021.00182Test http://hdl.handle.net/10072/416704Test |
| حقوق: | © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. ; open access |
| رقم الانضمام: | edsbas.F59E0DCA |
| قاعدة البيانات: | BASE |
| ردمك: | 9781665423984 1665423986 |
|---|---|
| تدمد: | 15504786 |
| DOI: | 10.1109/ICDM51629.2021.00182 |