arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.13072cs.LGcs.CRstat.ML
收藏

对抗推理攻击的隐私保护图嵌入

Adversarial Privacy Preserving Graph Embedding against Inference Attack

University of Electronic Science and Technology of China(电子科技大学);Georgia State University(佐治亚州立大学)

Kaiyang Li, Guangchun Luo, Yang Ye, Wei Li, Shihao Ji, Zhipeng Cai

摘要:

最近,物联网(IoT)、移动设备、社交媒体等的普及为图形数据开辟了大量来源。图嵌入已被证明是非常有用的学习低维特征表示从图结构化数据。这些特征表示可用于从节点分类到链接预测的各种预测任务。然而,现有的图嵌入方法没有考虑用户的隐私,以防止推理攻击。也就是说,攻击者可以通过分析从图嵌入算法学习的节点表示来推断用户的敏感信息。在本文中,我们提出了对抗隐私图嵌入(APGE),这是一个图对抗训练框架,它集成了解开和清除机制,以从学习的节点表示中删除用户的隐私信息。该方法保留了图的结构信息和效用属性,同时隐藏了用户的私有属性,避免了推理攻击。在真实世界的图数据集上进行的大量实验表明,与最先进的算法相比,APGE具有更好的性能。我们的源代码可以在https://github.com/uJ62JHD/Privacy-Preserving-Social-Network-Embedding上找到。

英文摘要:

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 feature representations from graph structured data. These feature representations can be used for a variety of prediction tasks from node classification to link prediction. However, existing graph embedding methods do not consider users' privacy to prevent inference attacks. That is, adversaries can infer users' sensitive information by analyzing node representations learned from graph embedding algorithms. In this paper, we propose Adversarial Privacy Graph Embedding (APGE), a graph adversarial training framework that integrates the disentangling and purging mechanisms to remove users' private information from learned node representations. The proposed method preserves the structural information and utility attributes of a graph while concealing users' private attributes from inference attacks. Extensive experiments on real-world graph datasets demonstrate the superior performance of APGE compared to the state-of-the-arts. Our source code can be found at https://github.com/uJ62JHD/Privacy-Preserving-Social-Network-Embedding.

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。

↑