用可信执行环境保护边缘图神经网络推理，防模型窃取且精度损失小于2%。
Graph in the Vault: Protecting Edge GNN Inference with Trusted Execution Environment
- 将GNN模型分片部署，敏感参数和私有图数据放入可信环境隔离保护。
- 在真实Intel SGX环境中实现，对主流链接窃取攻击具备防御能力。
- 适合需保护模型隐私的边缘智能场景，如医疗、金融图分析。
边缘设备上广泛部署机器学习模型导致模型知识产权和数据隐私面临风险。本文提出GNNVault，首个基于可信执行环境（TEE）的图神经网络安全部署方案。GNNVault采用‘先分割后训练’设计，并引入私有GNN修正器以配合公开骨干模型，使关键的GNN参数和推理时使用的私有图数据均在安全的TEE区域内受保护。基于Intel SGX的真实实现表明，GNNVault能有效防御当前最先进的链接窃取攻击，且精度损失低于2%。
原文摘要 · Abstract (English)
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%).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。