Graph structured data have enabled several successful applications such as recommendation systems and traffic prediction, given the rich node features and edges information. However, these high-dimensional features and high-order adjacency information are usually heterogeneous and held by different data holders in practice. Given such vertical data partition (e.g., one data holder will only own either the node features or edge information), different data holders have to develop efficient joint training protocols rather than directly transfer data to each other due to privacy concerns. In this paper, we focus on the edge privacy, and consider a training scenario where Bob with node features will first send training node features to Alice who owns the adjacency information. Alice will then train a graph neural network (GNN) with the joint information and release an inference API. During inference, Bob is able to provide test node features and query the API to obtain the predictions for test nodes. Under this setting, we first propose a privacy attack LinkTeller via influence analysis to infer the private edge information held by Alice via designing adversarial queries for Bob. We then empirically show that LinkTeller is able to recover a significant amount of private edges, outperforming existing baselines. To further evaluate the privacy leakage, we adapt an existing algorithm for differentially private graph convolutional network (DP GCN) training and propose a new DP GCN mechanism LapGraph. We show that these DP GCN mechanisms are not always resilient against LinkTeller empirically under mild privacy guarantees ($\varepsilon>5$). Our studies will shed light on future research towards designing more resilient privacy-preserving GCN models; in the meantime, provide an in-depth understanding of the tradeoff between GCN model utility and robustness against potential privacy attacks.
翻译:鉴于有丰富的节点特征和边缘信息,图表结构数据使建议系统和流量预测等一些成功的应用得以成功,例如建议系统和流量预测。然而,这些高维特征和高度相邻信息通常各不相同,由不同的数据持有者实际掌握。鉴于这种垂直数据分割(例如,一个数据持有者只能拥有节点特征或边缘信息),不同的数据持有者必须开发高效的联合培训协议,而不是直接将数据传输给对方,因为隐私问题。在本文中,我们侧重于边缘隐私,并考虑一种培训情景,即有节点功能的鲍勃首先向拥有相邻信息的爱丽丝发送培训节点特征。然后,爱丽丝将用联合信息来培训一个图形神经网络(GNNN),并发布一段感知性API。在推断中,鲍勃能够提供测试节点特征特性,并询问API,以便获得测试节点的预测。在本文中,我们首先建议通过影响分析隐私模型,来推断Alice持有的私人较轻的节点信息,为Bob设计抗性CN查询。然后,我们从经验的角度显示,Link Treal dealalalalalal deal lieval deal deal deal devial deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal de deal deal deal deal deal deal deal deal deal deal deal de de deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal deal de de deal deal deal deal deal de de de de de de de de de de de de de de de ex deal deal deal deal deal deal deal deal deal deal deal deal deal de ex de ex de ex de de ex de ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex