Iftikhar, MasoomaWang, QingLi, YangGama, JooLi, TianruiYu, YangChen, EnhongZheng, YuTeng, Fei2024-03-28May 1619978-3-031-05932-2http://hdl.handle.net/1885/316380Preserving privacy of an individual in network structured data while enhancing utility of published data is one of the most challenging problems in data privacy. Moreover, different individuals might have different privacy levels based on their own preferences, thereby personalization needs to be considered to achieve personal data protection. In this paper, we aim to develop a privacy-preserving mechanism to publish network statistics, particularly degree distribution, and joint degree distribution, which guarantees personalized (edge or node) differential privacy while enhancing network data utility. To this extend we propose four approaches to handle personal privacy requirements of individuals in a differentially private computation. We have empirically verified the utility enhancement and privacy guarantee of our proposed approaches on four real-world network datasets. To the best of our knowledge, this is the first study to publish network data distributions under personalized differential privacy, while enhancing network data utility.application/pdfen-AU© The Author(s), under exclusive license to Springer Nature Switzerland AG 2022Privacy-preserving graph data publishingPersonalized differential privacyNetwork data distributionsGraph data utility202210.1007/978-3-031-05933-9_162022-11-13