{"type":"ScholarlyArticle","title":"Secure Deep Graph Generation with Link Differential Privacy","authors":[{"name":"Carl Yang","slug":"carl-yang","given":"Carl","family":"Yang","affiliation":""},{"name":"Haonan Wang","slug":"haonan-wang","given":"Haonan","family":"Wang","affiliation":""},{"name":"Ke Zhang","slug":"ke-zhang","given":"Ke","family":"Zhang","affiliation":""},{"name":"Liang Chen","slug":"liang-chen","given":"Liang","family":"Chen","affiliation":""},{"name":"Lichao Sun","slug":"lichao-sun","given":"Lichao","family":"Sun","affiliation":""}],"abstract":"Many data mining and analytical tasks rely on the abstraction of networks (graphs) to summarize relational structures among individuals (nodes). Since relational data are often sensitive, we aim to seek effective approaches to generate utility-preserved yet privacy-protected structured data.\r\nIn this paper, we leverage the differential privacy (DP) framework to formulate and enforce rigorous privacy constraints on deep graph generation models, with a focus on edge-DP to guarantee individual link privacy.\r\nIn particular, we enforce edge-DP by injecting designated noise to the gradients of a link reconstruction based graph generation model, while ensuring data utility by improving structure learning with structure-oriented graph discrimination.\r\nExtensive experiments on two real-world network datasets show that our proposed DPGGAN model is able to generate graphs with effectively preserved global structure and rigorously protected individual link privacy.","doi":"10.24963/ijcai.2021/450","url":"https://ijcai.org/proceedings/2021/450","pdf":"https://ijcai.org/proceedings/2021/0450.pdf","markdown":"https://ijcai.org/proceedings/2021/450.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/450","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Machine Learning","track":"Main Track","number":450,"pages":{"first":3271,"last":3278},"keywords":["Data Mining: Mining Graphs, Semi Structured Data, Complex Data","Machine Learning: Learning Generative Models","Data Mining: Privacy Preserving Data Mining"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}