{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T05:31:10Z","timestamp":1773811870478,"version":"3.50.1"},"reference-count":63,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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","award":["62162005"],"award-info":[{"award-number":["62162005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20474"],"award-info":[{"award-number":["U21A20474"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009007","name":"Guangxi Normal University","doi-asserted-by":"publisher","award":["2024PY028"],"award-info":[{"award-number":["2024PY028"]}],"id":[{"id":"10.13039\/501100009007","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1016\/j.knosys.2025.114897","type":"journal-article","created":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T07:40:13Z","timestamp":1763538013000},"page":"114897","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Structural complementary hypergraph defense framework against adversarial attacks"],"prefix":"10.1016","volume":"332","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8663-1112","authenticated-orcid":false,"given":"Linlin","family":"Su","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3563-9536","authenticated-orcid":false,"given":"Zeming","family":"Gan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2462-1499","authenticated-orcid":false,"given":"Jinyan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7083-3847","authenticated-orcid":false,"given":"Xianxian","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2025.114897_bib0001","series-title":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"6534","article-title":"A survey on hypergraph neural networks: an in-depth and step-by-step guide","author":"Kim","year":"2024"},{"issue":"1","key":"10.1016\/j.knosys.2025.114897_bib0002","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3605776","article-title":"A survey on hypergraph representation learning","volume":"56","author":"Antelmi","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.knosys.2025.114897_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106207","article-title":"A comprehensive survey on deep graph representation learning","author":"Ju","year":"2024","journal-title":"Neural Netw."},{"key":"10.1016\/j.knosys.2025.114897_bib0004","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)","first-page":"18377","article-title":"When hypergraph meets heterophily: new benchmark datasets and baseline","volume":"39","author":"Li","year":"2025"},{"key":"10.1016\/j.knosys.2025.114897_bib0005","first-page":"1","article-title":"Hypergraph consistency learning with relational distillation","author":"Yi","year":"2025","journal-title":"IEEE Trans. Multimedia"},{"key":"10.1016\/j.knosys.2025.114897_bib0006","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"22594","article-title":"Hypergraph-enhanced dual semi-supervised graph classification","volume":"235","author":"Ju","year":"2024"},{"issue":"11","key":"10.1016\/j.knosys.2025.114897_bib0007","doi-asserted-by":"crossref","first-page":"11860","DOI":"10.1109\/TKDE.2023.3235312","article-title":"Self-supervised hypergraph representation learning for sociological analysis","volume":"35","author":"Sun","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.knosys.2025.114897_bib0008","series-title":"International Conference on Machine Learning","first-page":"3183","article-title":"Molecular hypergraph grammar with its application to molecular optimization","author":"Kajino","year":"2019"},{"issue":"6","key":"10.1016\/j.knosys.2025.114897_bib0009","doi-asserted-by":"crossref","first-page":"706","DOI":"10.1109\/TBDATA.2024.3453757","article-title":"Edugraph: learning path-based hypergraph neural networks for MOOC course recommendation","volume":"10","author":"Li","year":"2024","journal-title":"IEEE Trans. Big Data"},{"key":"10.1016\/j.knosys.2025.114897_bib0010","series-title":"Proceedings of the IEEE International Conference on Data Engineering","first-page":"2303","article-title":"Dynamic hypergraph structure learning for traffic flow forecasting","author":"Zhao","year":"2023"},{"key":"10.1016\/j.knosys.2025.114897_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102428","article-title":"Educross: dual adversarial bipartite hypergraph learning for cross-modal retrieval in multimodal educational slides","volume":"109","author":"Li","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.knosys.2025.114897_bib0012","unstructured":"C. Hu, R. Yu, B. Zeng, Y. Zhan, Y. Fu, Q. Zhang, R. Liu, H. Shi, Hyperattack: Multi-gradient-guided white-box adversarial structure attack of hypergraph neural networks, (2023). arXiv preprint arXiv:2302.12407."},{"key":"10.1016\/j.knosys.2025.114897_bib0013","series-title":"AAAI Conference on Artificial Intelligence","first-page":"3558","article-title":"Hypergraph neural networks","volume":"33","author":"Feng","year":"2019"},{"key":"10.1016\/j.knosys.2025.114897_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2020.107637","article-title":"Hypergraph convolution and hypergraph attention","volume":"110","author":"Bai","year":"2021","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2025.114897_bib0015","series-title":"International Joint Conference on Artificial Intelligence","first-page":"4816","article-title":"Adversarial examples for graph data: deep insights into attack and defense","author":"Wu","year":"2019"},{"key":"10.1016\/j.knosys.2025.114897_bib0016","series-title":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"1399","article-title":"Robust graph convolutional networks against adversarial attacks","author":"Zhu","year":"2019"},{"key":"10.1016\/j.knosys.2025.114897_bib0017","series-title":"Advances in Neural Information Processing Systems","first-page":"9263","article-title":"GNNGuard: Defending graph neural networks against adversarial attacks","author":"Zhang","year":"2020"},{"key":"10.1016\/j.knosys.2025.114897_bib0018","series-title":"International Conference on Learning Representations","article-title":"Adversarial attacks on graph neural networks via meta learning","author":"Z\u00fcgner","year":"2019"},{"key":"10.1016\/j.knosys.2025.114897_bib0019","series-title":"International Joint Conference on Artificial Intelligence","first-page":"3961","article-title":"Topology attack and defense for graph neural networks: an optimization perspective","author":"Xu","year":"2019"},{"key":"10.1016\/j.knosys.2025.114897_bib0020","series-title":"The International Conference on Learning Representations","article-title":"You are allset: a multiset function framework for hypergraph neural networks","author":"Chien","year":"2022"},{"key":"10.1016\/j.knosys.2025.114897_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110115","article-title":"UniG-Encoder: a universal feature encoder for graph and hypergraph node classification","volume":"147","author":"Zou","year":"2024","journal-title":"Pattern Recognit."},{"issue":"2","key":"10.1016\/j.knosys.2025.114897_bib0022","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1109\/JPROC.2024.3369017","article-title":"Trustworthy graph neural networks: aspects, methods, and trends","volume":"112","author":"Zhang","year":"2024","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.knosys.2025.114897_bib0023","series-title":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"2847","article-title":"Adversarial attacks on neural networks for graph data","author":"Z\u00fcgner","year":"2018"},{"key":"10.1016\/j.knosys.2025.114897_bib0024","series-title":"ACM International Conference on Information and Knowledge Management","first-page":"3012","article-title":"Debiased graph poisoning attack via contrastive surrogate objective","author":"Yoon","year":"2024"},{"key":"10.1016\/j.knosys.2025.114897_bib0025","series-title":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"1161","article-title":"Graph adversarial attack via rewiring","author":"Ma","year":"2021"},{"key":"10.1016\/j.knosys.2025.114897_bib0026","series-title":"International Joint Conference on Artificial Intelligence","first-page":"768","article-title":"Cluster attack: query-based adversarial attacks on graph with graph-Dependent priors","author":"Wang","year":"2022"},{"key":"10.1016\/j.knosys.2025.114897_bib0027","series-title":"IEEE International Conference on Data Engineering","first-page":"1017","article-title":"Black-box adversarial attack and defense on graph neural networks","author":"Li","year":"2022"},{"key":"10.1016\/j.knosys.2025.114897_bib0028","series-title":"ACM Web Conference","first-page":"2011","article-title":"Curriculum graph poisoning","author":"Liu","year":"2023"},{"key":"10.1016\/j.knosys.2025.114897_bib0029","series-title":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"2461","article-title":"TDGIA: Effective injection attacks on graph neural networks","author":"Zou","year":"2021"},{"key":"10.1016\/j.knosys.2025.114897_bib0030","series-title":"International Conference on Learning Representations","article-title":"Understanding and improving graph injection attack by promoting unnoticeability","author":"Chen","year":"2022"},{"key":"10.1016\/j.knosys.2025.114897_bib0031","series-title":"AAAI Conference on Artificial Intelligence and Conference on Innovative Applications of Artificial Intelligence and Symposium on Educational Advances in Artificial Intelligence","article-title":"Let graph be the go board: gradient-free node injection attack for graph neural networks via reinforcement learning","author":"Ju","year":"2023"},{"issue":"4","key":"10.1016\/j.knosys.2025.114897_bib0032","doi-asserted-by":"crossref","first-page":"5374","DOI":"10.1109\/TCSS.2024.3361027","article-title":"GANI: Global attacks on graph neural networks via imperceptible node injections","volume":"11","author":"Fang","year":"2024","journal-title":"IEEE Trans. Comput. Social Syst."},{"key":"10.1016\/j.knosys.2025.114897_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129128","article-title":"Topology-Aware node injection attacks against graph neural networks","volume":"618","author":"Su","year":"2025","journal-title":"Neurocomputing"},{"issue":"1","key":"10.1016\/j.knosys.2025.114897_bib0034","article-title":"DGHSA: Derivative graph-based hypergraph structure attack","volume":"14","author":"Chen","year":"2024","journal-title":"Sci. Rep."},{"key":"10.1016\/j.knosys.2025.114897_bib0035","unstructured":"Y. Chen, S. Picek, Z. Ye, Z. Wang, H. Zhao, Momentum gradient-based untargeted attack on hypergraph neural networks, (2023). arXiv preprint arXiv:2310.15656."},{"key":"10.1016\/j.knosys.2025.114897_bib0036","series-title":"International Conference on Machine Vision, Automatic Identification, and Detection","first-page":"132302X","article-title":"HyperMGA: momentum gradient attack of hypergraph neural networks","volume":"13230","author":"Liu","year":"2024"},{"key":"10.1016\/j.knosys.2025.114897_bib0037","series-title":"AAAI Conference on Artificial Intelligence","article-title":"Hypergraph attacks via injecting homogeneous nodes into elite hyperedges","author":"He","year":"2025"},{"key":"10.1016\/j.knosys.2025.114897_bib0038","article-title":"H3NI: Non-target-specific node injection attacks on hypergraph neural networks via genetic algorithm","volume":"613","author":"Shi","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.knosys.2025.114897_bib0039","series-title":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"925","article-title":"Reliable representations make a stronger defender: unsupervised structure refinement for robust GNN","author":"Li","year":"2022"},{"key":"10.1016\/j.knosys.2025.114897_bib0040","series-title":"ACM Web Conference","first-page":"697","article-title":"Self-Guided robust graph structure refinement","author":"In","year":"2024"},{"key":"10.1016\/j.knosys.2025.114897_bib0041","series-title":"ACM Web Conference","first-page":"328","article-title":"Robust mid-Pass filtering graph convolutional networks","author":"Huang","year":"2023"},{"key":"10.1016\/j.knosys.2025.114897_bib0042","series-title":"Advances in Neural Information Processing Systems","article-title":"Robust graph neural networks via unbiased aggregation","author":"Hou","year":"2024"},{"key":"10.1016\/j.knosys.2025.114897_bib0043","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106938","article-title":"D4A: An efficient and effective defense across agnostic adversarial attacks","volume":"183","author":"Li","year":"2025","journal-title":"Neural Netw."},{"key":"10.1016\/j.knosys.2025.114897_bib0044","series-title":"International Conference on Learning Representations","article-title":"Boosting the adversarial robustness of graph neural networks: an OOD perspective","author":"Li","year":"2024"},{"key":"10.1016\/j.knosys.2025.114897_bib0045","series-title":"International Conference on Learning Representations","article-title":"Mitigating emergent robustness degradation while scaling graph learning","author":"Yuan","year":"2024"},{"key":"10.1016\/j.knosys.2025.114897_bib0046","series-title":"AAAI Conference on Artificial Intelligence","article-title":"A simple and yet fairly effective defense for graph neural networks","author":"Ennadir","year":"2024"},{"key":"10.1016\/j.knosys.2025.114897_bib0047","series-title":"International Joint Conference on Artificial Intelligence","first-page":"1923","article-title":"Hypergraph structure learning for hypergraph neural networks","author":"Cai","year":"2022"},{"key":"10.1016\/j.knosys.2025.114897_bib0048","series-title":"Advances in Neural Information Processing Systems","first-page":"1909","article-title":"Augmentations in hypergraph contrastive learning: fabricated and generative","volume":"35","author":"Wei","year":"2022"},{"key":"10.1016\/j.knosys.2025.114897_bib0049","series-title":"International Conference on Learning Representations","article-title":"LightHGNN: distilling hypergraph neural networks into MLPs for 100x faster inference","author":"Feng","year":"2024"},{"key":"10.1016\/j.knosys.2025.114897_bib0050","series-title":"International Conference on Learning Representations","article-title":"DistillHGNN: a knowledge distillation approach for high-Speed hypergraph neural networks","author":"Forouzandeh","year":"2025"},{"key":"10.1016\/j.knosys.2025.114897_bib0051","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"13476","article-title":"Hypergraph-Mlp: learning on hypergraphs without message passing","author":"Tang","year":"2024"},{"key":"10.1016\/j.knosys.2025.114897_bib0052","series-title":"The AI Magazine","article-title":"Collective classification in network data","author":"Prithviraj","year":"2008"},{"key":"10.1016\/j.knosys.2025.114897_bib0053","series-title":"Advances in Neural Information Processing Systems","article-title":"HyperGCN: a new method of training graph convolutional networks on hypergraphs","author":"Yadati","year":"2019"},{"key":"10.1016\/j.knosys.2025.114897_bib0054","series-title":"International Joint Conference on Artificial Intelligence","first-page":"2563","article-title":"UniGNN: a unified framework for graph and hypergraph neural networks","author":"Huang","year":"2021"},{"key":"10.1016\/j.knosys.2025.114897_bib0055","series-title":"International Conference on Learning Representations","article-title":"Equivariant hypergraph diffusion neural operators","author":"Wang","year":"2023"},{"issue":"8","key":"10.1016\/j.knosys.2025.114897_bib0056","first-page":"9232","article-title":"Hypergraph joint representation learning for hypervertices and hyperedges via cross expansion","volume":"38","author":"Yan","year":"2024","journal-title":"Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence"},{"issue":"10","key":"10.1016\/j.knosys.2025.114897_bib0057","doi-asserted-by":"crossref","first-page":"8938","DOI":"10.1109\/TPAMI.2025.3585179","article-title":"Kernelized hypergraph neural networks","volume":"47","author":"Feng","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2025.114897_bib0058","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.111254","article-title":"Unveiling the potential of long-range dependence with mask-guided structure learning for hypergraph","volume":"284","author":"Lei","year":"2024","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2025.114897_bib0059","series-title":"International Conference on Machine Learning","first-page":"1725","article-title":"Simple and deep graph convolutional networks","author":"Chen","year":"2020"},{"key":"10.1016\/j.knosys.2025.114897_bib0060","series-title":"International Conference on Learning Representations","article-title":"Semi-Supervised classification with graph convolutional networks","author":"Kipf","year":"2017"},{"key":"10.1016\/j.knosys.2025.114897_bib0061","first-page":"7637","article-title":"Robustness of graph neural networks at scale","volume":"34","author":"Geisler","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"2","key":"10.1016\/j.knosys.2025.114897_bib0062","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1038\/s41562-017-0290-3","article-title":"Hiding individuals and communities in a social network","volume":"2","author":"Waniek","year":"2018","journal-title":"Nat. Hum. Behav."},{"key":"10.1016\/j.knosys.2025.114897_bib0063","series-title":"International Conference on Learning Representations","article-title":"Revisiting graph adversarial attack and defense from a data distribution perspective","author":"Li","year":"2023"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705125019355?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705125019355?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T04:48:08Z","timestamp":1773809288000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705125019355"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":63,"alternative-id":["S0950705125019355"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2025.114897","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Structural complementary hypergraph defense framework against adversarial attacks","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2025.114897","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114897"}}