We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
DP-AGM: A Differential Privacy Preserving Method for Binary Relationship in Mobile Networks.
- Authors
Ning, Bo; Zhang, Xinjian; Gao, Shuai; Li, Guanyu
- Abstract
The mobile network is a graph structure that models a set of objects (nodes) and their relationships (edges). Recently, data mining methods have proliferated due to the strong expressive power of graphs, which has led to the leakage of some private data in graphs during the mining process. For example, mobile communication networks are mobile networks where nodes usually refer to individuals and edges represent various relationships. When data analysis is performed on them, it may lead to leakage of users' personal information or hidden relationships. Unfortunately, most privacy protection of graph data in the past has focused on structure or node information. We are concerned with the protection of binary relationships. Therefore, we look for an efficient way to process graphs and publish the processed data so that the relationships between nodes in the graph can be protected without losing their usability. Based on the graph generation model AGM (Affiliation Graph Model) and differential privacy protection theory, we propose the DP-AGM model with reasonable privacy budget assignment to preserve the structure of the graph under the condition of well-protected relationships. Through experimental verification, our method can achieve a better balance.
- Subjects
TELECOMMUNICATION systems; DATA mining; DATA protection; DATA analysis; PRIVACY
- Publication
Mobile Networks & Applications, 2023, Vol 28, Issue 5, p1597
- ISSN
1383-469X
- Publication type
Article
- DOI
10.1007/s11036-023-02098-7