PIAFGNN: Property Inference Attacks against Federated Graph Neural Networks
Source abstract
Abstract
Federated Graph Neural Networks (FedGNNs) have achieved significant success in representation learning for graph data, enabling collaborative training among multiple parties without sharing their raw graph data and solving th... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Privacy-Preserving Technologies in Data · Advanced Graph Neural Networks · Adversarial Robustness in Machine Learning
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (29)
Show source-provided references
1. Federated machine learning: Concept and applications10.1145/3339474 ↗
2. Communication-efficient learning of deep networks from decentralized data
3. Blockchain-enabled federated learning data protection aggregation scheme with differential privacy and homomorphic encryption in iiot10.1109/TII.2021.3085960 ↗
4. Federated graph neural networks: Overview, techniques, and challenges
5. Federatedscope-GNN: Towards a unified, comprehensive and efficient package for federated graph learning
6. More is better (mostly): On the backdoor attacks in federated graph neural networks
7. C. He et al., “FedGraphNN: A federated learning system and benchmark for graph neural networks,” 2021. doi: 10.48550/arXiv.2104.07145.
8. A federated graph neural network framework for privacy-preserving personalization10.1038/s41467-022-30714-9 ↗
9. C. Chen et al., “Vertically federated graph neural network for privacy-preserving node classification,” 2020. doi: 10.48550/arXiv.2005.11903.
10. Inference attacks against graph neural networks
11. Group property inference attacks against graph neural networks
12. A comprehensive survey of graph neural networks for knowledge graphs10.1109/ACCESS.2022.3191784 ↗
13. A survey of graph neural network based recommendation in social networks10.1016/j.neucom.2023.126441 ↗
14. FP-GNN: A versatile deep learning architecture for enhanced molecular property prediction10.1093/bib/bbac408 ↗
15. Gan enhanced membership inference: A passive local attack in federated learning
16. Exploiting unintended feature leakage in collaborative learning
17. Membership inference attacks against machine learning models
18. Label-only membership inference attack against node-level graph neural networks
19. T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” 2016. doi: 10.48550/arXiv.1609.02907.
20. Inductive representation learning on large graphs
21. P. Velickovic, G. Cucurull, A. Casanova, A. Romero, P. Lio and Y. Bengio, “Graph attention networks,” vol. 1050, no. 20, pp. 10–48, 550, 2017. doi: 10.48550/arXiv.1710.10903.
22. Feature inference attack on model predictions in vertical federated learning
23. Graph-Fraudster: Adversarial attacks on graph neural network-based vertical federated learning10.1109/TCSS.2022.3161016 ↗
24. Property inference attacks on fully connected neural networks using permutation invariant representations
25. Automating the construction of internet portals with machine learning10.1023/A:1009953814988 ↗
26. CiteSeer: An automatic citation indexing system
27. Collective classification in network data
28. PrivSyn: Differentially private data synthesis
29. Advances and open problems in federated learning10.1561/2200000083 ↗