{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:02:11Z","timestamp":1750309331330,"version":"3.41.0"},"reference-count":56,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T00:00:00Z","timestamp":1726790400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62072061, 61976030 and U20A20176"],"award-info":[{"award-number":["62072061, 61976030 and U20A20176"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Funds for Creative Research Groups of Chongqing Municipal Education Commission","award":["CXQT21034"],"award-info":[{"award-number":["CXQT21034"]}]},{"name":"National Science Foundation","award":["CNS-2153393"],"award-info":[{"award-number":["CNS-2153393"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Sen. Netw."],"published-print":{"date-parts":[[2024,9,30]]},"abstract":"<jats:p>Graph embedding converts a graph data into a low dimensional space to preserve the original graph information. However, graph data can be reconstructed by malicious adversaries to train machine learning models from graph embeddings. This paper studies to what extent an adversary (without the original graph data) can recover the original graph data from graph embeddings. To quantify the original graph information leakage from graph embeddings, we develop a deep neural network model InferNet that can be used by adversaries to infer the original graph information from an adversary-accessible graph embedding database. More specifically, we propose the data-free reversed knowledge distillation technique to support the InferNet training even if the original graph dataset is absent. To ensure the performance of InferNet, we design two cycle-consistency loss functions to have an interactive training of InferNet over three series of datasets. To further enhance the performance of InferNet, we provide a joint training algorithm that simultaneously trains the pseudo-sample generator and InferNet, which significantly reduces the storage space. We evaluate the performance of InferNet on three datasets, and the intensive experiments demonstrate that InferNet can infer the original graph information from the graph embedding dataset with high accuracy.<\/jats:p>","DOI":"10.1145\/3688846","type":"journal-article","created":{"date-parts":[[2024,8,14]],"date-time":"2024-08-14T11:04:53Z","timestamp":1723633493000},"page":"1-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["On the Inference of Original Graph Information from Graph Embeddings"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7648-5671","authenticated-orcid":false,"given":"Yantao","family":"Li","sequence":"first","affiliation":[{"name":"College of Computer Science, Chongqing University, Chongqing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6806-8704","authenticated-orcid":false,"given":"Xinyang","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science, Chongqing University, Chongqing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8799-7875","authenticated-orcid":false,"given":"Xinyu","family":"Lei","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Michigan Technological University, Houghton, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4911-0393","authenticated-orcid":false,"given":"Huafeng","family":"Qin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Chongqing Technology and Business University, Chongqing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8790-5579","authenticated-orcid":false,"given":"Yiwen","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Michigan State University, East Lansing, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4425-9837","authenticated-orcid":false,"given":"Gang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Computer Science Department, William &amp; Mary, Williamsburg, United States"}]}],"member":"320","published-online":{"date-parts":[[2024,9,20]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20629"},{"key":"e_1_3_1_3_2","first-page":"870","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"36","author":"He Qingdong","year":"2022","unstructured":"Qingdong He, Zhengning Wang, Hao Zeng, Yi Zeng, and Yijun Liu. 2022. SVGA-Net: Sparse voxel-graph attention network for 3D object detection from point clouds. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 870\u2013878."},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20898"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20340"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3243782"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2986316"},{"key":"e_1_3_1_8_2","article-title":"Text level graph neural network for text classification","author":"Huang Lianzhe","year":"2019","unstructured":"Lianzhe Huang, Dehong Ma, Sujian Li, Xiaodong Zhang, and Houfeng Wang. 2019. Text level graph neural network for text classification. arXiv preprint arXiv:1910.02356 (2019).","journal-title":"arXiv preprint arXiv:1910.02356"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.5555\/3327345.3327423"},{"key":"e_1_3_1_10_2","first-page":"874","volume-title":"International Conference on Machine Learning","author":"Bianchi Filippo Maria","year":"2020","unstructured":"Filippo Maria Bianchi, Daniele Grattarola, and Cesare Alippi. 2020. Spectral clustering with graph neural networks for graph pooling. In International Conference on Machine Learning. 874\u2013883."},{"issue":"1","key":"e_1_3_1_11_2","first-page":"9","article-title":"DeviceWatch: A data-driven network analysis approach to identifying compromised mobile devices with graph-inference","volume":"26","author":"Choo Euijin","year":"2022","unstructured":"Euijin Choo, Mohamed Nabeel, Mashael Alsabah, Issa Khalil, Ting Yu, and Wei Wang. 2022. DeviceWatch: A data-driven network analysis approach to identifying compromised mobile devices with graph-inference. ACM Transactions on Privacy and Security 26, 1, Article 9 (Nov.2022), 32 pages.","journal-title":"ACM Transactions on Privacy and Security"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294869"},{"key":"e_1_3_1_13_2","volume-title":"International Conference on Learning Representations","author":"Veli\u010dkovi\u0107 Petar","year":"2018","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph attention networks. In International Conference on Learning Representations."},{"key":"e_1_3_1_14_2","article-title":"How powerful are graph neural networks?","author":"Xu Keyulu","year":"2018","unstructured":"Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2018. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826 (2018).","journal-title":"arXiv preprint arXiv:1810.00826"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623732"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939754"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/2736277.2741093"},{"key":"e_1_3_1_18_2","first-page":"4438","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"32","author":"Zhang Muhan","year":"2018","unstructured":"Muhan Zhang, Zhicheng Cui, Marion Neumann, and Yixin Chen. 2018. An end-to-end deep learning architecture for graph classification. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32. 4438\u20134445."},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3232604"},{"issue":"7","key":"e_1_3_1_20_2","first-page":"3236","article-title":"Multiple structure-view learning for graph classification","volume":"29","author":"Wu Jia","year":"2017","unstructured":"Jia Wu, Shirui Pan, Xingquan Zhu, Chengqi Zhang, and S. Yu Philip. 2017. Multiple structure-view learning for graph classification. IEEE Transactions on Neural Networks and Learning Systems 29, 7 (2017), 3236\u20133251.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_3_1_21_2","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/978-1-4419-8462-3_5","article-title":"Node classification in social networks","author":"Bhagat Smriti","year":"2011","unstructured":"Smriti Bhagat, Graham Cormode, and S. Muthukrishnan. 2011. Node classification in social networks. Social Network Data Analytics (2011), 115\u2013148.","journal-title":"Social Network Data Analytics"},{"issue":"6","key":"e_1_3_1_22_2","doi-asserted-by":"crossref","first-page":"1718","DOI":"10.1378\/chest.111.6.1718","article-title":"Regional lymph node classification for lung cancer staging","volume":"111","author":"Mountain Clifton F.","year":"1997","unstructured":"Clifton F. Mountain and Carolyn M. Dresler. 1997. Regional lymph node classification for lung cancer staging. Chest 111, 6 (1997), 1718\u20131723.","journal-title":"Chest"},{"key":"e_1_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Guimin Dong Mingyue Tang Zhiyuan Wang Jiechao Gao Sikun Guo Lihua Cai Robert Gutierrez Bradford Campbel Laura E. Barnes and Mehdi Boukhechba. 2023. Graph neural networks in IoT: A survey. 19 2 Article 47 (Apr.2023) 50 pages.","DOI":"10.1145\/3565973"},{"key":"e_1_3_1_24_2","article-title":"Accurate localization in LOS\/NLOS channel coexistence scenarios based on heterogeneous knowledge graph inference","author":"Zhang Bojun","year":"2024","unstructured":"Bojun Zhang, Xiulong Liu, Xin Xie, Xinyu Tong, Yungang Jia, Tuo Shi, and Wenyu Qu. 2024. Accurate localization in LOS\/NLOS channel coexistence scenarios based on heterogeneous knowledge graph inference. ACM Trans. Sen. Netw. (Mar.2024). Just Accepted.","journal-title":"ACM Trans. Sen. Netw."},{"issue":"4","key":"e_1_3_1_25_2","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1145\/3594668","article-title":"GPART: Partitioning maximal redundant rigid and maximal global rigid components in generic distance graphs","volume":"19","author":"Zhang Yu","year":"2023","unstructured":"Yu Zhang, Qinhan Wei, Yongcai Wang, Haodi Ping, and Deying Li. 2023. GPART: Partitioning maximal redundant rigid and maximal global rigid components in generic distance graphs. ACM Trans. Sen. Netw. 19, 4, Article 86 (Jun.2023), 26 pages.","journal-title":"ACM Trans. Sen. Netw."},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1218772110"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132990"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3448891.3448939"},{"key":"e_1_3_1_29_2","first-page":"4543","volume-title":"31st USENIX Security Symposium (USENIX Security 22)","author":"Zhang Zhikun","year":"2022","unstructured":"Zhikun Zhang, Min Chen, Michael Backes, Yun Shen, and Yang Zhang. 2022. Inference attacks against graph neural networks. In 31st USENIX Security Symposium (USENIX Security 22). 4543\u20134560."},{"key":"e_1_3_1_30_2","first-page":"1","volume-title":"IEEE International Joint Conference on Neural Network (IJCNN)","volume":"36","author":"Li Xinyang","year":"2023","unstructured":"Xinyang Li, Xinyu Lei, Yantao Li, Huafeng Qin, and Hu Yiwen. 2023. Towards inference original graph data information from graph embeddings. In IEEE International Joint Conference on Neural Network (IJCNN), Vol. 36. 1\u201310."},{"key":"e_1_3_1_31_2","article-title":"Spectral networks and locally connected networks on graphs","author":"Bruna Joan","year":"2013","unstructured":"Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann LeCun. 2013. Spectral networks and locally connected networks on graphs. arXiv preprint arXiv:1312.6203 (2013).","journal-title":"arXiv preprint arXiv:1312.6203"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157527"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00097"},{"key":"e_1_3_1_34_2","volume-title":"Proceedings of ICLR\u201916","author":"Li Yujia","year":"2016","unstructured":"Yujia Li, Richard Zemel, Marc Brockschmidt, and Daniel Tarlow. 2016. Gated graph sequence neural networks. In Proceedings of ICLR\u201916."},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301265"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/8810817"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380297"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2827389"},{"key":"e_1_3_1_39_2","doi-asserted-by":"crossref","first-page":"1163","DOI":"10.1109\/ICIP.2019.8803734","volume-title":"2019 IEEE International Conference on Image Processing (ICIP)","author":"Rezaeifar Shideh","year":"2019","unstructured":"Shideh Rezaeifar, Behrooz Razeghi, Olga Taran, Taras Holotyak, and Slava Voloshynovskiy. 2019. Reconstruction of privacy-sensitive data from protected templates. In 2019 IEEE International Conference on Image Processing (ICIP). IEEE, 1163\u20131167."},{"key":"e_1_3_1_40_2","first-page":"1473","volume-title":"International Conference on Machine Learning","author":"Chanpuriya Sudhanshu","year":"2021","unstructured":"Sudhanshu Chanpuriya, Cameron Musco, Konstantinos Sotiropoulos, and Charalampos Tsourakakis. 2021. Deepwalking backwards: from embeddings back to graphs. In International Conference on Machine Learning. PMLR, 1473\u20131483."},{"key":"e_1_3_1_41_2","doi-asserted-by":"crossref","unstructured":"Battista Biggio Giorgio Fumera Paolo Russu Luca Didaci and Fabio Roli. 2015. Adversarial biometric recognition: A review on biometric system security from the adversarial machine-learning perspective. IEEE Signal Processing Magazine 32 5 (2015) 31\u201341.","DOI":"10.1109\/MSP.2015.2426728"},{"key":"e_1_3_1_42_2","first-page":"1216","volume-title":"2010 IEEE 26th International Conference on Data Engineering","author":"Lehner Wolfgang","year":"2010","unstructured":"Wolfgang Lehner and Kai-Uwe Sattler. 2010. Database as a service (DBaaS). In 2010 IEEE 26th International Conference on Data Engineering. 1216\u20131217."},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00361"},{"key":"e_1_3_1_44_2","first-page":"125","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Liang Xiaodan","year":"2016","unstructured":"Xiaodan Liang, Xiaohui Shen, Jiashi Feng, Liang Lin, and Shuicheng Yan. 2016. Semantic object parsing with graph LSTM. In Proceedings of the European Conference on Computer Vision. 125\u2013143."},{"key":"e_1_3_1_45_2","volume-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI\u201918)","author":"Yan Sijie","year":"2018","unstructured":"Sijie Yan, Yuanjun Xiong, and Dahua Lin. 2018. Spatial temporal graph convolutional networks for skeleton-based action recognition. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI\u201918). Article 912, 9 pages."},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"e_1_3_1_47_2","first-page":"5435","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Antonakos Epameinondas","year":"2015","unstructured":"Epameinondas Antonakos, Joan Alabort-i Medina, and Stefanos Zafeiriou. 2015. Active pictorial structures. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5435\u20135444."},{"issue":"1","key":"e_1_3_1_48_2","first-page":"7","article-title":"A novel cross-network embedding for anchor link prediction with social adversarial attacks","volume":"26","author":"Wang Huanran","year":"2022","unstructured":"Huanran Wang, Wu Yang, Wei Wang, Dapeng Man, and Jiguang Lv. 2022. A novel cross-network embedding for anchor link prediction with social adversarial attacks. ACM Transactions on Privacy and Security 26, 1, Article 7 (Nov.2022), 32 pages.","journal-title":"ACM Transactions on Privacy and Security"},{"issue":"8","key":"e_1_3_1_49_2","doi-asserted-by":"crossref","first-page":"1115","DOI":"10.1016\/S0167-8655(02)00258-1","article-title":"Similarity learning for graph-based image representations","volume":"24","author":"Mauro Ciro de","year":"2003","unstructured":"Ciro de Mauro, Michelangelo Diligenti, Marco Gori, and Marco Maggini. 2003. Similarity learning for graph-based image representations. Pattern Recognition Letters 24, 8 (2003), 1115\u20131122.","journal-title":"Pattern Recognition Letters"},{"issue":"3","key":"e_1_3_1_50_2","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1109\/TCDS.2020.2998497","article-title":"CNN-G: Convolutional neural network combined with graph for image segmentation with theoretical analysis","volume":"13","author":"Lu Yi","year":"2020","unstructured":"Yi Lu, Yaran Chen, Dongbin Zhao, Bao Liu, Zhichao Lai, and Jianxin Chen. 2020. CNN-G: Convolutional neural network combined with graph for image segmentation with theoretical analysis. IEEE Transactions on Cognitive and Developmental Systems 13, 3 (2020), 631\u2013644.","journal-title":"IEEE Transactions on Cognitive and Developmental Systems"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"issue":"3","key":"e_1_3_1_52_2","first-page":"10","article-title":"Efficient attack graph analysis through approximate inference","volume":"20","author":"Gonz\u00e1lez Luis Mu\u00f1oz","year":"2017","unstructured":"Luis Mu\u00f1oz Gonz\u00e1lez, Daniele Sgandurra, Andrea Paudice, and Emil C. Lupu. 2017. Efficient attack graph analysis through approximate inference. ACM Transactions on Privacy and Security 20, 3, Article 10 (Jul.2017), 30 pages.","journal-title":"ACM Transactions on Privacy and Security"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_1_54_2","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao Han","year":"2017","unstructured":"Han Xiao, Kashif Rasul, and Roland Vollgraf. 2017. Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747 (2017).","journal-title":"arXiv preprint arXiv:1708.07747"},{"key":"e_1_3_1_55_2","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard Andrew G.","year":"2017","unstructured":"Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017).","journal-title":"arXiv preprint arXiv:1704.04861"},{"key":"e_1_3_1_56_2","article-title":"Adam: A method for stochastic optimization","author":"Kingma Diederik P.","year":"2014","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.131"}],"container-title":["ACM Transactions on Sensor Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3688846","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3688846","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:10Z","timestamp":1750291450000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3688846"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,20]]},"references-count":56,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,9,30]]}},"alternative-id":["10.1145\/3688846"],"URL":"https:\/\/doi.org\/10.1145\/3688846","relation":{},"ISSN":["1550-4859","1550-4867"],"issn-type":[{"type":"print","value":"1550-4859"},{"type":"electronic","value":"1550-4867"}],"subject":[],"published":{"date-parts":[[2024,9,20]]},"assertion":[{"value":"2023-11-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-11","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-09-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}