In recent years, with the rapid development of graph neural networks (GNN), more and more graph datasets have been published for GNN tasks. However, when an upstream data owner publishes graph data, there are often many privacy concerns, because many real-world graph data contain sensitive information like person's friend list. Differential privacy (DP) is a common method to protect privacy, but due to the complex topological structure of graph data, applying DP on graphs often affects the message passing and aggregation of GNN models, leading to a decrease in model accuracy. In this paper, we propose a novel graph edge protection framework, graph publisher (GraphPub), which can protect graph topology while ensuring that the availability of data is basically unchanged. Through reverse learning and the encoder-decoder mechanism, we search for some false edges that do not have a large negative impact on the aggregation of node features, and use them to replace some real edges. The modified graph will be published, which is difficult to distinguish between real and false data. Sufficient experiments prove that our framework achieves model accuracy close to the original graph with an extremely low privacy budget.
Forecasting Energy Availability in Local Energy Communities via LSTM Federated Learning
DISMI, University of Modena and Reggio Emilia, Italy(DISMI,Modena和Reggio Emilia大学);En\&Tech, University of Modena and Reggio Emilia, Italy(En\&Tech,Modena和Reggio Emilia大学)
Semi-decentralized Federated Time Series Prediction with Client Availability Budgets
Department of Electrical and Software Engineering, University of Calgary(电气与软件工程系,卡尔加里大学);Department of Geomatics Engineering, University of Calgary(测绘工程系,卡尔加里大学)
A Systematic and Formal Study of the Impact of Local Differential Privacy on Fairness: Preliminary Results
INRIA(法国国家信息与自动化研究所);École Polytechnique(巴黎综合理工学院);IPP(IPP机构);Mathematical Institute of the Serbian Academy of Sciences and Arts(塞尔维亚科学院数学研究所);Inria Centre at the University Grenoble Alpes(格勒诺布尔大学Inria中心)
Enhanced Security and Privacy via Fragmented Federated Learning
UNESCO Chair in Data Privacy(联合国教科文组织数据隐私教席);CYBERCAT Center for Cybersecurity Research of Catalonia(加泰罗尼亚网络安全研究中心(CYBERCAT));Universitat Rovira i Virgili(罗维拉-威尔吉利大学)
Assessment of creditworthiness models privacy-preserving training with synthetic data
The University of Western Ontario(西安大略大学);University of Basque Country(巴斯克大学);Business Intelligence Research Center (CEINE)(商业智能研究中心(CEINE));University of Chile(智利大学)