paper-with-me

홈 › Papers

SecGNN: Privacy-Preserving Graph Neural Network Training and Inference as a Cloud Service

2022-02-16 · Songlei Wang, Yifeng Zheng, Xiaohua Jia

Graphs are widely used to model the complex relationships among entities. As a powerful tool for graph analytics, graph neural networks (GNNs) have recently gained wide attention due to its end-to-end processing capabilities. With the proliferation of cloud computing, it is increasingly popular to deploy the services of complex and resource-intensive model training and inference in the cloud due to its prominent benefits. However, GNN training and inference services, if deployed in the cloud, will raise critical privacy concerns about the information-rich and proprietary graph data (and the resulting model). While there has been some work on secure neural network training and inference, they all focus on convolutional neural networks handling images and text rather than complex graph data with rich structural information. In this paper, we design, implement, and evaluate SecGNN, the first system supporting privacy-preserving GNN training and inference services in the cloud. SecGNN is built from a synergy of insights on lightweight cryptography and machine learning techniques. We deeply examine the procedure of GNN training and inference, and devise a series of corresponding secure customized protocols to support the holistic computation. Extensive experiments demonstrate that SecGNN achieves comparable plaintext training and inference accuracy, with promising performance.

📄 PDF Abstract BibTeX arXiv:2202.07835

Code (0)

등록된 구현이 없습니다.

Tasks

Cloud ComputingGraph Neural NetworkPrivacy Preserving

Similar Papers 제목 키워드 기반

Privacy-Preserving Decentralized Inference with Graph Neural Networks in Wireless Networks

2022-08-15 · Mengyuan Lee, Guanding Yu, Huaiyu Dai

As an efficient neural network model for graph data, graph neural networks (GNNs) recently find successful applications for various wireless optimization problems. Given that the inference stage of GNNs can be naturally …

Efficient Neural NetworkManagementPrivacy Preserving

CryptoSPN: Privacy-preserving Sum-Product Network Inference

2020-02-03 · Amos Treiber, Alejandro Molina, Christian Weinert, Thomas Schneider 외

AI algorithms, and machine learning (ML) techniques in particular, are increasingly important to individuals' lives, but have caused a range of privacy concerns addressed by, e.g., the European GDPR. Using cryptographic …

Privacy Preserving

Adversarial Privacy Preserving Graph Embedding against Inference Attack

2020-08-30 · Kaiyang Li, Guangchun Luo, Yang Ye, Wei Li 외

Recently, the surge in popularity of Internet of Things (IoT), mobile devices, social media, etc. has opened up a large source for graph data. Graph embedding has been proved extremely useful to learn low-dimensional fea…

Graph EmbeddingInference AttackLink PredictionNetwork Embedding+2

Locally Private Graph Neural Networks

2020-06-09 · Sina Sajadmanesh, Daniel Gatica-Perez

Graph Neural Networks (GNNs) have demonstrated superior performance in learning node representations for various graph inference tasks. However, learning over graph data can raise privacy concerns when nodes represent pe…

Federated LearningNode ClassificationPrivacy PreservingPrivacy Preserving Deep Learning

CryptGPU: Fast Privacy-Preserving Machine Learning on the GPU

2021-04-22 · Sijun Tan, Brian Knott, Yuan Tian, David J. Wu

We introduce CryptGPU, a system for privacy-preserving machine learning that implements all operations on the GPU (graphics processing unit). Just as GPUs played a pivotal role in the success of modern deep learning, the…

BIG-bench Machine LearningCPUGPUPrivacy Preserving+1