arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.00030cs.SIcs.AIcs.CRcs.LG
收藏

GraphPub:生成具有高可用性的差分隐私图

GraphPub: Generation of Differential Privacy Graph with High Availability

Xi’an Jiaotong University(西安交通大学)

Wanghan Xu, Bin Shi, Ao Liu, Jiqiang Zhang, Bo Dong

AI总结:

针对差分隐私图发布导致GNN准确率下降的问题,本文提出GraphPub框架,利用逆向学习和编码器-解码器机制以低影响虚假边替换真实边,在极低隐私预算下保持接近原图的模型准确率。

摘要:

近年来,随着图神经网络(GNN)的快速发展,越来越多的图数据集被发布用于GNN任务。然而,当上游数据所有者发布图数据时,往往存在许多隐私顾虑,因为许多真实世界的图数据包含个人好友列表等敏感信息。差分隐私(DP)是一种常用的隐私保护方法,但由于图数据复杂的拓扑结构,在图上应用DP往往会影响GNN模型的消息传递和聚合,导致模型准确率下降。本文提出了一种新颖的图边保护框架——graph publisher(GraphPub),它能够在保护图拓扑结构的同时,确保数据的可用性基本不变。通过逆向学习和编码器-解码器机制,我们搜索一些对节点特征聚合不会产生较大负面影响的虚假边,并用它们替换部分真实边。修改后的图将被发布,其中真实数据与虚假数据难以区分。充分的实验证明,我们的框架在极低的隐私预算下实现了接近原始图的模型准确率。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑