| 摘要: |
| 图数据是一种特殊的数据形式, 由节点和边组成. 在这种数据中, 实体被建模为节点, 节点之间可能存在边, 表示实体之间的关系. 通过分析和挖掘这些数据, 人们可以获得很多有价值的信息. 因此, 对于图中各个节点来说, 它也带来了隐私信息泄露的风险. 为了解决这个问题, 提出了一种基于负数据库(NDB)的图数据发布方法. 该方法将图数据的结构特征转换为负数据库的编码形式,基于此, 设计出一种扰动图(NDB-Graph)的生成方法. 由于NDB是一种保护隐私的技术, 不显式存储原始数据且难以逆转, 故发布的图数据能确保原始图数据的安全. 此外, 由于图神经网络在图数据中关系特征处理方面的高效性,被广泛应用于对图数据的各种任务处理建模, 例如推荐系统, 还提出了一种基于NDB技术的图神经网络的推荐系统来保护每个用户的图数据隐私. 基于Karate和Facebook数据集上的实验表明, 与PBCN发布方法相比, 所提方法在大多数情况下表现更优秀. 例如: 在Facebook数据集上, 度分布最小的L1误差仅为6, 比同隐私等级下的PBCN方法低约2.6%; 最坏情况约为1 400, 比同隐私等级下的PBCN方法低约46.5%. 在基于LightGCN的协同过滤实验中也表明, 所提出的隐私保护方法具有较高的精度. |
| 关键词: 图数据 隐私保护 负数据库 推荐系统 图神经网络 |
| DOI：10.13328/j.cnki.jos.007124 |
| 分类号: |
| 基金项目:国家自然科学基金(61806151); 湖北省重点研发计划(2022BAA050);海南省重点研发计划(ZDYF2021GXJS014); 重庆市自然科学基金(cstc2021jcyj-msxmX0002) |
|
| Privacy-preserving Graph Neural Network Recommendation System Based on Negative Database |
|
ZHAO Dong-Dong1,2, XU Hu1, PENG Si-Yun1, ZHOU Jun-Wei1
|
|
1.School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan 430070, China;2.Chongqing Research Institute, Wuhan University of Technology, Chongqing 401135, China
|
| Abstract: |
| Graph data is a kind of data composed of nodes and edges, which models the entities as the nodes, nodes may be connected by edges, and edge indicates a relationship between entities. By analyzing and mining these data, a lot of valuable information can be revealed. Meanwhile, it also brings risks of privacy information disclosure for every entity in the graph. To address this issue, a graph data publishing method is proposed based on the negative database (NDB). This method transforms the structural characteristics of the graph data into the encoding format of a negative database. Based on this, a generation method for perturbed graphs (NDB-Graph) is designed. Since NDB is a privacy-preserving technique that does not explicitly store the original data and is difficult to reverse, the published graph data ensures the security of the original graph data. Besides, due to the high efficiency of graph neural network in relation feature processing in graph data, it is widely used in various task processing modeling on graph data, such as recommendation system. a graph neural network recommendation system is also proposed based on NDB technology to protect the privacy of graph data for each user. Compared with publishing method PBCN, the proposed method outperforms it in most cases in experiments on the Karate and Facebook datasets. For example, on Facebook datasets, the smallest L1-error of degree distribution is only 6, which is about 2.6% lower than the PBCN method under the same privacy level, the worst case is about 1 400, which is about 46.5% lower than the PBCN method under the same privacy level. The experiment of collaborative filtering based on LightGCN also demonstrates that the proposed privacy protection method has high precision. |
| Key words: graph data privacy preservation negative database recommendation system graph neural network |
