{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T11:02:51Z","timestamp":1779706971218,"version":"3.53.1"},"reference-count":59,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.neunet.2026.109133","type":"journal-article","created":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T15:28:21Z","timestamp":1778945301000},"page":"109133","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Mapp: A model-agnostic privacy-preserving framework for two-party graph neural network inference"],"prefix":"10.1016","volume":"203","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0935-0715","authenticated-orcid":false,"given":"Juxiang","family":"Zeng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pinghui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangchao","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingqin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohong","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.neunet.2026.109133_bib0001","doi-asserted-by":"crossref","first-page":"325","DOI":"10.56553\/popets-2023-0020","article-title":"Helayers: A tile tensors framework for large neural networks on encrypted data","volume":"1","author":"Aharoni","year":"2023","journal-title":"Proceedings on Privacy Enhancing Technologies"},{"key":"10.1016\/j.neunet.2026.109133_bib0002","series-title":"Proceedings of the 22nd International conference on world wide web","first-page":"37","article-title":"Distributed large-scale natural graph factorization","author":"Ahmed","year":"2013"},{"key":"10.1016\/j.neunet.2026.109133_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2022.105626","article-title":"Vision-based human fall detection systems using deep learning: A review","volume":"146","author":"Alam","year":"2022","journal-title":"Computers in Biology and Medicine"},{"key":"10.1016\/j.neunet.2026.109133_bib0004","unstructured":"Baek, J., Kang, M., & Hwang, S. J. (2021). Accurate learning of graph representations with graph multiset pooling. arXiv: 2102.11533."},{"key":"10.1016\/j.neunet.2026.109133_bib0005","series-title":"Garbled neural networks are practical","author":"Ball","year":"2019"},{"key":"10.1016\/j.neunet.2026.109133_bib0006","series-title":"Proceedings of the 28th ACM SIGKDD Conference on knowledge discovery and data mining","first-page":"2712","article-title":"Company-as-tribe: Company financial risk assessment on tribe-style graph with hierarchical graph neural networks","author":"Bi","year":"2022"},{"key":"10.1016\/j.neunet.2026.109133_bib0007","series-title":"International conference on machine learning","first-page":"874","article-title":"Spectral clustering with graph neural networks for graph pooling","author":"Bianchi","year":"2020"},{"key":"10.1016\/j.neunet.2026.109133_bib0008","series-title":"Crypto","first-page":"483","article-title":"Fast homomorphic evaluation of deep discretized neural networks","author":"Bourse","year":"2018"},{"key":"10.1016\/j.neunet.2026.109133_bib0009","series-title":"ICML","first-page":"812","article-title":"Low latency privacy preserving inference","author":"Brutzkus","year":"2019"},{"key":"10.1016\/j.neunet.2026.109133_bib0010","doi-asserted-by":"crossref","unstructured":"Chen, Y., Bian, Y., Xiao, X., Rong, Y., Xu, T., & Huang, J. (2020). On self-distilling graph neural network. arXiv: 2011.02255.","DOI":"10.24963\/ijcai.2021\/314"},{"key":"10.1016\/j.neunet.2026.109133_bib0011","unstructured":"Chou, E., Beal, J., Levy, D., Yeung, S., Haque, A., & Fei-Fei, L. (2018). Faster cryptonets: Leveraging sparsity for real-world encrypted inference. arXiv: 1811.09953."},{"issue":"1","key":"10.1016\/j.neunet.2026.109133_bib0012","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1186\/s12880-024-01349-7","article-title":"Advancing medical imaging: Detecting polypharmacy and adverse drug effects with graph convolutional networks (GCN)","volume":"24","author":"Dara","year":"2024","journal-title":"BMC Medical Imaging"},{"key":"10.1016\/j.neunet.2026.109133_bib0013","doi-asserted-by":"crossref","unstructured":"Deng, X., & Zhang, Z. (2021). Graph-free knowledge distillation for graph neural networks. arXiv: 2105.07519.","DOI":"10.24963\/ijcai.2021\/320"},{"issue":"6","key":"10.1016\/j.neunet.2026.109133_bib0014","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1145\/3812.3818","article-title":"A randomized protocol for signing contracts","volume":"28","author":"Even","year":"1985","journal-title":"Communications of the ACM"},{"key":"10.1016\/j.neunet.2026.109133_bib0015","series-title":"Proceedings of the 28th ACM SIGKDD Conference on knowledge discovery and data mining","first-page":"357","article-title":"FreeKD: Free-direction knowledge distillation for graph neural networks","author":"Feng","year":"2022"},{"key":"10.1016\/j.neunet.2026.109133_bib0016","series-title":"ICML","first-page":"201","article-title":"CryptoNets: Applying neural networks to encrypted data with high throughput and accuracy","author":"Gilad-Bachrach","year":"2016"},{"key":"10.1016\/j.neunet.2026.109133_bib0017","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.knosys.2018.03.022","article-title":"Graph embedding techniques, applications, and performance: A survey","volume":"151","author":"Goyal","year":"2018","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.109133_bib0018","series-title":"Advances in neural information processing systems","article-title":"Inductive representation learning on large graphs","volume":"vol. 30","author":"Hamilton","year":"2017"},{"key":"10.1016\/j.neunet.2026.109133_bib0019","unstructured":"Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv: 1503.02531."},{"key":"10.1016\/j.neunet.2026.109133_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106135","article-title":"SecBERT: Privacy-preserving pre-training based neural network inference system","volume":"172","author":"Huang","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109133_bib0021","first-page":"207","article-title":"Cheetah: Lean and fast secure two-party deep neural network inference","volume":"2022","author":"Huang","year":"2022","journal-title":"IACR Cryptol"},{"key":"10.1016\/j.neunet.2026.109133_bib0022","series-title":"Advances in cryptology - CRYPTO 2003, 23rd Annual international cryptology conference, santa barbara, California, Usa, August 17\u201321, 2003, proceedings","first-page":"145","article-title":"Extending oblivious transfers efficiently","volume":"vol. 2729","author":"Ishai","year":"2003"},{"key":"10.1016\/j.neunet.2026.109133_bib0023","series-title":"Proceedings of the 2018\u202fACM SIGSAC Conference on computer and communications security","first-page":"1209","article-title":"Secure outsourced matrix computation and application to neural networks","author":"Jiang","year":"2018"},{"issue":"4","key":"10.1016\/j.neunet.2026.109133_bib0024","doi-asserted-by":"crossref","first-page":"4656","DOI":"10.1109\/TNNLS.2022.3223018","article-title":"On representation knowledge distillation for graph neural networks","volume":"35","author":"Joshi","year":"2024","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.109133_bib0025","series-title":"Usenix security","first-page":"1651","article-title":"Gazelle: A low latency framework for secure neural network inference","author":"Juvekar","year":"2018"},{"key":"10.1016\/j.neunet.2026.109133_bib0026","series-title":"ICML","article-title":"FicGCN: Unveiling the homomorphic encryption efficiency from irregular graph convolutional networks","author":"Kan","year":"2025"},{"key":"10.1016\/j.neunet.2026.109133_bib0027","unstructured":"Kipf, T. N., & Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv: 1609.02907."},{"key":"10.1016\/j.neunet.2026.109133_bib0028","series-title":"CVPR","first-page":"8705","article-title":"Falcon: A Fourier transform based approach for fast and secure convolutional neural network predictions","author":"Li","year":"2020"},{"issue":"2","key":"10.1016\/j.neunet.2026.109133_bib0029","doi-asserted-by":"crossref","first-page":"1265","DOI":"10.1109\/TDSC.2024.3431590","article-title":"CrossNet: A low-latency MLaaS framework for privacy-preserving neural network inference on resource-limited devices","volume":"22","author":"Lin","year":"2025","journal-title":"IEEE Transactions on Dependable and Secure Computing"},{"key":"10.1016\/j.neunet.2026.109133_bib0030","doi-asserted-by":"crossref","unstructured":"Liu, C., Zhan, Y., Li, C., Du, B., Wu, J., Hu, W., Liu, T., & Tao, D. (2022). Graph pooling for graph neural networks: Progress, challenges, and opportunities.","DOI":"10.24963\/ijcai.2023\/752"},{"key":"10.1016\/j.neunet.2026.109133_bib0031","series-title":"Ccs","first-page":"619","article-title":"Oblivious neural network predictions via minionn transformations","author":"Liu","year":"2017"},{"key":"10.1016\/j.neunet.2026.109133_bib0032","series-title":"Proceedings of the 40th IEEE international conference on data engineering (ICDE 2024)","article-title":"Pp-stream: Toward high-performance privacy-preserving neural network inference via distributed stream processing","author":"Liu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109133_bib0033","series-title":"ICLR","article-title":"SafeNet: A secure, accurate and fast neural network inference","author":"Lou","year":"2020"},{"key":"10.1016\/j.neunet.2026.109133_bib0034","series-title":"Usenix security","first-page":"2505","article-title":"Delphi: A cryptographic inference service for neural networks","author":"Mishra","year":"2020"},{"key":"10.1016\/j.neunet.2026.109133_bib0035","series-title":"Sp","first-page":"19","article-title":"SecureML: A system for scalable privacy-preserving machine learning","author":"Mohassel","year":"2017"},{"key":"10.1016\/j.neunet.2026.109133_bib0036","series-title":"30th USENIX Security symposium (USENIX security 21)","first-page":"2147","article-title":"GForce: GPU-friendly oblivious and rapid neural network inference","author":"Ng","year":"2021"},{"key":"10.1016\/j.neunet.2026.109133_bib0037","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107307","article-title":"Privcore: Multiplication-activation co-reduction for efficient private inference","volume":"187","author":"Pang","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109133_bib0038","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/j.media.2018.06.001","article-title":"Disease prediction using graph convolutional networks: Application to autism spectrum disorder and Alzheimer\u2019s disease","volume":"48","author":"Parisot","year":"2018","journal-title":"Medical Image Analysis"},{"key":"10.1016\/j.neunet.2026.109133_bib0039","series-title":"Advances in neural information processing systems","article-title":"LinGCN: Structural linearized graph convolutional network for homomorphically encrypted inference","volume":"vol. 36","author":"Peng","year":"2023"},{"key":"10.1016\/j.neunet.2026.109133_bib0040","series-title":"IACR Cryptology ePrint archive","first-page":"187","article-title":"How to exchange secrets with oblivious transfer","volume":"vol.2005","author":"Rabin","year":"2005"},{"key":"10.1016\/j.neunet.2026.109133_bib0041","first-page":"37676","article-title":"CryptoGCN: Fast and scalable homomorphically encrypted graph convolutional network inference","volume":"35","author":"Ran","year":"2022","journal-title":"Advances in Neural information processing systems"},{"key":"10.1016\/j.neunet.2026.109133_bib0042","series-title":"Advances in neural information processing systems","article-title":"Penguin: Parallel-packed homomorphic encryption for fast graph convolutional network inference","volume":"vol. 36","author":"Ran","year":"2024"},{"key":"10.1016\/j.neunet.2026.109133_bib0043","series-title":"Ccs","first-page":"325","article-title":"CrypTFlow2: Practical 2-party secure inference","author":"Rathee","year":"2020"},{"key":"10.1016\/j.neunet.2026.109133_bib0044","series-title":"Usenix security","first-page":"1501","article-title":"XONN: XNOR-based oblivious deep neural network inference","author":"Riazi","year":"2019"},{"key":"10.1016\/j.neunet.2026.109133_bib0045","series-title":"DAC","first-page":"1","article-title":"DeepSecure: Scalable provably-secure deep learning","author":"Rouhani","year":"2018"},{"key":"10.1016\/j.neunet.2026.109133_bib0046","series-title":"ICML","first-page":"4490","article-title":"Tapas: Tricks to accelerate (encrypted) prediction as a service","author":"Sanyal","year":"2018"},{"issue":"17","key":"10.1016\/j.neunet.2026.109133_bib0047","doi-asserted-by":"crossref","first-page":"5194","DOI":"10.1002\/hbm.25994","article-title":"Spatial\u2013temporal graph convolutional network for alzheimer classification based on brain functional connectivity imaging of electroencephalogram","volume":"43","author":"Shan","year":"2022","journal-title":"Human Brain Mapping"},{"key":"10.1016\/j.neunet.2026.109133_bib0048","series-title":"International conference on learning representations","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2018"},{"issue":"4","key":"10.1016\/j.neunet.2026.109133_bib0049","doi-asserted-by":"crossref","first-page":"2923","DOI":"10.1109\/TSC.2023.3241615","article-title":"SecGNN: Privacy-preserving graph neural network training and inference as a cloud service","volume":"16","author":"Wang","year":"2023","journal-title":"IEEE Transactions on Services Computing"},{"key":"10.1016\/j.neunet.2026.109133_bib0050","series-title":"ICLR","article-title":"How powerful are graph neural networks?","author":"Xu","year":"2019"},{"key":"10.1016\/j.neunet.2026.109133_bib0051","series-title":"Proceedings of the 26th ACM SIGKDD International conference on knowledge discovery & data mining","first-page":"1848","article-title":"TinyGNN: Learning efficient graph neural networks","author":"Yan","year":"2020"},{"key":"10.1016\/j.neunet.2026.109133_bib0052","series-title":"Proceedings of the web conference 2021","first-page":"1227","article-title":"Extract the knowledge of graph neural networks and go beyond it: An effective knowledge distillation framework","author":"Yang","year":"2021"},{"key":"10.1016\/j.neunet.2026.109133_bib0053","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"7074","article-title":"Distilling knowledge from graph convolutional networks","author":"Yang","year":"2020"},{"key":"10.1016\/j.neunet.2026.109133_bib0054","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zhang, G., Wu, J., Yang, J., Sheng, Q. Z., Xue, S., Zhou, C., Aggarwal, C., Peng, H., Hu, W., Hancock, E., & Li\u00f2, P. (2024). State of the art and potentialities of graph-level learning. ACM Computing Surveys, 57(2), 28, 40. 10.1145\/3695863.","DOI":"10.1145\/3695863"},{"key":"10.1016\/j.neunet.2026.109133_bib0055","series-title":"FOCS","first-page":"162","article-title":"How to generate and exchange secrets","author":"Yao","year":"1986"},{"key":"10.1016\/j.neunet.2026.109133_bib0056","series-title":"Advances in neural information processing systems","article-title":"Hierarchical graph representation learning with differentiable pooling","volume":"vol. 31","author":"Ying","year":"2018"},{"key":"10.1016\/j.neunet.2026.109133_bib0057","series-title":"Proceedings of the web conference 2020","first-page":"3098","article-title":"Structure-feature based graph self-adaptive pooling","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neunet.2026.109133_bib0058","unstructured":"Zhang, S., Liu, Y., Sun, Y., & Shah, N. (2021). Graph-less neural networks: Teaching old mlps new tricks via distillation. arXiv: 2110.08727."},{"key":"10.1016\/j.neunet.2026.109133_bib0059","series-title":"Proceedings of the 2020\u202fACM SIGMOD International conference on management of data","first-page":"1399","article-title":"Reliable data distillation on graph convolutional network","author":"Zhang","year":"2020"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026005940?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026005940?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T10:15:01Z","timestamp":1779704101000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026005940"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":59,"alternative-id":["S0893608026005940"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109133","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Mapp: A model-agnostic privacy-preserving framework for two-party graph neural network inference","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109133","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109133"}}