{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T07:24:51Z","timestamp":1780817091567,"version":"3.54.1"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,8]]},"abstract":"<jats:p>As machine learning becomes more widely used for critical applications, the need to study its implications in privacy becomes urgent.\n\nGiven access to the target model and auxiliary information, model inversion attack aims to infer sensitive features of the training dataset, which leads to great privacy concerns.\n\nDespite its success in the grid domain, directly applying model inversion techniques on non grid domains such as graph achieves poor attack performance due to the difficulty to fully exploit the intrinsic properties of graphs and attributes of graph nodes used in GNN models.\n\nTo bridge this gap, we present Graph Model Inversion attack, which aims to infer edges of the training graph by inverting Graph Neural Networks, one of the most popular graph analysis tools.\n\nSpecifically, the projected gradient module in our method can tackle the discreteness of graph edges while preserving the sparsity and smoothness of graph features.\n\nMoreover, a well designed graph autoencoder module can efficiently exploit graph topology, node attributes, and target model parameters.\n\nWith the proposed method, we study the connection between model inversion risk and edge influence and show that edges with greater influence are more likely to be recovered.\n\nExtensive experiments over several public datasets demonstrate the effectiveness of our method.\n\nWe also show that differential privacy in its canonical form can hardly defend our attack while preserving decent utility.<\/jats:p>","DOI":"10.24963\/ijcai.2021\/516","type":"proceedings-article","created":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T11:00:49Z","timestamp":1628679649000},"page":"3749-3755","source":"Crossref","is-referenced-by-count":43,"title":["GraphMI: Extracting Private Graph Data from Graph Neural Networks"],"prefix":"10.24963","author":[{"given":"Zaixi","family":"Zhang","sequence":"first","affiliation":[{"name":"Anhui Province Key Lab. of Big Data Analysis and Application, School of Computer Science and Technology, University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"Anhui Province Key Lab. of Big Data Analysis and Application, School of Computer Science and Technology, University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenya","family":"Huang","sequence":"additional","affiliation":[{"name":"Anhui Province Key Lab. of Big Data Analysis and Application, School of Computer Science and Technology, University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"Anhui Province Key Lab. of Big Data Analysis and Application, School of Computer Science and Technology, University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengqiang","family":"Lu","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanren","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Tennessee Knoxville"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enhong","family":"Chen","sequence":"additional","affiliation":[{"name":"Anhui Province Key Lab. of Big Data Analysis and Application, School of Computer Science and Technology, University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10584","event":{"name":"Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}","theme":"Artificial Intelligence","location":"Montreal, Canada","acronym":"IJCAI-2021","number":"30","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2021,8,19]]},"end":{"date-parts":[[2021,8,27]]}},"container-title":["Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T11:03:49Z","timestamp":1628679829000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2021\/516"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2021\/516","relation":{},"subject":[],"published":{"date-parts":[[2021,8]]}}}