Towards Inference of Original Graph Data Information from Graph Embeddings
Document Type
Conference Proceeding
Publication Date
8-2-2023
Department
Department of Computer Science
Abstract
This paper studies to what extent an adversary (without the original graph data) can recover the original raw graph data from graph embeddings. To quantify the original graph data information leakage from graph embeddings, we develop a deep neural network model InferNet that can be used by adversaries to infer the original graph data information from an adversary-accessible graph embedding database. Specifically, we propose the data-free reversed knowledge distillation (KD) technique to support InferNet training even if the original graph dataset is absent. To improve the performance of InferNet, we design two cycle-consistency loss functions to have an interactive training of InferNet over three series of datasets. Our intensive experiments demonstrate that InferNet can infer the original graph data information from the graph embedding dataset with high accuracy.
Publication Title
Proceedings of the International Joint Conference on Neural Networks
ISBN
9781665488679
Recommended Citation
Li, X.,
Lei, X.,
Li, Y.,
Qin, H.,
&
Hu, Y.
(2023).
Towards Inference of Original Graph Data Information from Graph Embeddings.
Proceedings of the International Joint Conference on Neural Networks, 1-10.
http://doi.org/10.1109/IJCNN54540.2023.10191065
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p2/142