Year: 2025
Type: preprint
Abstract: Wide deployment of machine learning models on edge devices has rendered the model intellectual property (IP) and data privacy vulnerable. We propose GNNVault, the first secure Graph Neural Network (GNN) deployment strategy based on Trusted Execution Environment (TEE). GNNVault follows the design of 'partition-before-training' and includes a private GNN rectifier to complement with a public backbone model. This way, both critical GNN model parameters and the private graph used during inference are protected within secure TEE compartments. Real-world implementations with Intel SGX demonstrate that GNNVault safeguards GNN inference against state-of-the-art link stealing attacks with negligible accuracy degradation (<2%).
Source: arXiv (Cornell University)
Authors: Ding, Ruyi, Xu, Tianhong, Ding, Aidong Adam, Fei, Yunsi
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6979341467
Cites:
Cited by:
Related to: